Training in progress, step 100

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e320f93cb15f71a4280e54d92e1974d7a5784768e6d5f19e86429cb656643e
+oid sha256:9d28fb09742c4bebcd9652128d63341d698294f233b691f916e2299a0efe0c8c
 size 6174112552

runs/Jun11_02-33-18_w1lxscirender02.worldbank.org/events.out.tfevents.1781145198.w1lxscirender02.worldbank.org.2729864.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8558c4ceeb7d6ff49056795110197757ae32b506bcae7c206c05b4512e28a4d
+size 6420

runs/Jun11_02-35-56_w1lxscirender02.worldbank.org/events.out.tfevents.1781145356.w1lxscirender02.worldbank.org.2746458.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:621bfcac8611e1401fee78dd17ed430420e55c16c59507fea551c1d7c493a82a
+size 5226

whisper-large-v3-chichewa-14h-normalized-transcript/README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: openai/whisper-large-v3
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-large-v3-chichewa-variant-b-normalized-transcript
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# whisper-large-v3-chichewa-variant-b-normalized-transcript
+
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3983
+- Wer: 59.3004
+- Cer: 28.1383
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 7.5e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.05
+- training_steps: 3000
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer     | Cer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
+| 6.1874        | 0.9259  | 100  | 1.4766          | 82.4754 | 37.1937 |
+| 4.3049        | 1.8519  | 200  | 1.1418          | 74.2396 | 35.4061 |
+| 3.2137        | 2.7778  | 300  | 1.0356          | 62.0496 | 28.7776 |
+| 2.3819        | 3.7037  | 400  | 1.0180          | 61.5466 | 27.8582 |
+| 1.7253        | 4.6296  | 500  | 1.0404          | 61.4998 | 29.3362 |
+| 1.2334        | 5.5556  | 600  | 1.1001          | 57.9902 | 27.0954 |
+| 0.7779        | 6.4815  | 700  | 1.1463          | 59.2302 | 28.1762 |
+| 0.5770        | 7.4074  | 800  | 1.2063          | 57.3701 | 26.3506 |
+| 0.3544        | 8.3333  | 900  | 1.2435          | 61.1254 | 28.6804 |
+| 0.2340        | 9.2593  | 1000 | 1.3227          | 59.6280 | 28.2108 |
+| 0.1444        | 10.1852 | 1100 | 1.3311          | 57.8147 | 26.0277 |
+| 0.1176        | 11.1111 | 1200 | 1.3743          | 57.6626 | 26.5121 |
+| 0.1288        | 12.0370 | 1300 | 1.3983          | 59.3004 | 28.1383 |
+
+
+### Framework versions
+
+- Transformers 5.8.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.22.2

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/config.json

@@ -0,0 +1,49 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "suppress_tokens": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/generation_config.json

@@ -0,0 +1,285 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 50257,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "language": "shona",
+  "length_penalty": 1.0,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "no_timestamps_token_id": 50364,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "target_lookbehind": 10,
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.8.1",
+  "typical_p": 1.0,
+  "use_cache": true
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61d0c7c62eb351733459864edab0f0c36fe8767cb5bba3ce3002a9815b5406fa
+size 6174112552

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1b08903bf5dc8868a2427698d48c9f89b76faa14d476763faa1840b3f244f0
+size 12349039011

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb3cb121ead4613aae6cd1185eab836513aa27211002ff50c7f5b45e4906f33
+size 14244

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba13a7cf4d23b8472deaaa35537f40c0adc7a75eb774ed4fddeea3dc8506209
+size 1064

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/trainer_state.json

@@ -0,0 +1,499 @@
+{
+  "best_global_step": 800,
+  "best_metric": 57.37014506317267,
+  "best_model_checkpoint": "/home/jupyter-wb344850/chichewa-asr/models/checkpoints/checkpoint-800",
+  "epoch": 11.11111111111111,
+  "eval_steps": 100,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 24.947662353515625,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 11.754910888671875,
+      "step": 25
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 17.93560791015625,
+      "learning_rate": 2.45e-06,
+      "loss": 9.367840576171876,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 20.061756134033203,
+      "learning_rate": 3.7e-06,
+      "loss": 7.043236083984375,
+      "step": 75
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 19.431058883666992,
+      "learning_rate": 4.95e-06,
+      "loss": 6.187430419921875,
+      "step": 100
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "eval_cer": 37.193745571977,
+      "eval_loss": 1.4765740633010864,
+      "eval_runtime": 191.4328,
+      "eval_samples_per_second": 2.069,
+      "eval_steps_per_second": 0.261,
+      "eval_wer": 82.47543284978943,
+      "step": 100
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 16.891460418701172,
+      "learning_rate": 6.2e-06,
+      "loss": 5.158666381835937,
+      "step": 125
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 18.55628776550293,
+      "learning_rate": 7.45e-06,
+      "loss": 4.892176208496093,
+      "step": 150
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 14.085015296936035,
+      "learning_rate": 7.498687774567386e-06,
+      "loss": 4.511752014160156,
+      "step": 175
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 14.737961769104004,
+      "learning_rate": 7.494531126609263e-06,
+      "loss": 4.304852905273438,
+      "step": 200
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "eval_cer": 35.40606000692007,
+      "eval_loss": 1.1418079137802124,
+      "eval_runtime": 203.4432,
+      "eval_samples_per_second": 1.946,
+      "eval_steps_per_second": 0.246,
+      "eval_wer": 74.23958820776791,
+      "step": 200
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 15.683085441589355,
+      "learning_rate": 7.487530934323892e-06,
+      "loss": 3.8006710815429687,
+      "step": 225
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 14.036075592041016,
+      "learning_rate": 7.4776925135589425e-06,
+      "loss": 3.319402160644531,
+      "step": 250
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 14.326029777526855,
+      "learning_rate": 7.465023335472914e-06,
+      "loss": 3.141165771484375,
+      "step": 275
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 14.966941833496094,
+      "learning_rate": 7.449533020861643e-06,
+      "loss": 3.2137042236328126,
+      "step": 300
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "eval_cer": 28.77761850625278,
+      "eval_loss": 1.035639762878418,
+      "eval_runtime": 184.1223,
+      "eval_samples_per_second": 2.151,
+      "eval_steps_per_second": 0.272,
+      "eval_wer": 62.04960224613944,
+      "step": 300
+    },
+    {
+      "epoch": 3.009259259259259,
+      "grad_norm": 11.072875022888184,
+      "learning_rate": 7.431233332852411e-06,
+      "loss": 3.094468688964844,
+      "step": 325
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 14.482994079589844,
+      "learning_rate": 7.41013816797118e-06,
+      "loss": 2.240164794921875,
+      "step": 350
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 14.527769088745117,
+      "learning_rate": 7.386263545589777e-06,
+      "loss": 2.3541885375976563,
+      "step": 375
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 14.758848190307617,
+      "learning_rate": 7.359627595761002e-06,
+      "loss": 2.381937255859375,
+      "step": 400
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "eval_cer": 27.858237358509218,
+      "eval_loss": 1.018039584159851,
+      "eval_runtime": 185.9344,
+      "eval_samples_per_second": 2.13,
+      "eval_steps_per_second": 0.269,
+      "eval_wer": 61.54656059897052,
+      "step": 400
+    },
+    {
+      "epoch": 3.935185185185185,
+      "grad_norm": 13.893526077270508,
+      "learning_rate": 7.330250545450925e-06,
+      "loss": 2.323583068847656,
+      "step": 425
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 12.67662525177002,
+      "learning_rate": 7.298154703178804e-06,
+      "loss": 2.037447052001953,
+      "step": 450
+    },
+    {
+      "epoch": 4.398148148148148,
+      "grad_norm": 13.166596412658691,
+      "learning_rate": 7.263364442076317e-06,
+      "loss": 1.6892933654785156,
+      "step": 475
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 14.612394332885742,
+      "learning_rate": 7.2259061813789465e-06,
+      "loss": 1.7252595520019531,
+      "step": 500
+    },
+    {
+      "epoch": 4.62962962962963,
+      "eval_cer": 29.336167268053977,
+      "eval_loss": 1.0403634309768677,
+      "eval_runtime": 184.8499,
+      "eval_samples_per_second": 2.142,
+      "eval_steps_per_second": 0.27,
+      "eval_wer": 61.49976602714086,
+      "step": 500
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 15.613510131835938,
+      "learning_rate": 7.185808366363582e-06,
+      "loss": 1.6008528137207032,
+      "step": 525
+    },
+    {
+      "epoch": 5.092592592592593,
+      "grad_norm": 14.135201454162598,
+      "learning_rate": 7.143101446747573e-06,
+      "loss": 1.6909564208984376,
+      "step": 550
+    },
+    {
+      "epoch": 5.324074074074074,
+      "grad_norm": 8.78895092010498,
+      "learning_rate": 7.097817853565651e-06,
+      "loss": 1.1801542663574218,
+      "step": 575
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 13.037683486938477,
+      "learning_rate": 7.049991974542245e-06,
+      "loss": 1.2334317779541015,
+      "step": 600
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_cer": 27.09538167498723,
+      "eval_loss": 1.1000748872756958,
+      "eval_runtime": 179.2605,
+      "eval_samples_per_second": 2.209,
+      "eval_steps_per_second": 0.279,
+      "eval_wer": 57.99017313991577,
+      "step": 600
+    },
+    {
+      "epoch": 5.787037037037037,
+      "grad_norm": 11.986921310424805,
+      "learning_rate": 6.999660127977939e-06,
+      "loss": 1.087800521850586,
+      "step": 625
+    },
+    {
+      "epoch": 6.018518518518518,
+      "grad_norm": 9.024539947509766,
+      "learning_rate": 6.9468605351698555e-06,
+      "loss": 1.152771224975586,
+      "step": 650
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 10.050127983093262,
+      "learning_rate": 6.891633291386944e-06,
+      "loss": 0.7668762969970703,
+      "step": 675
+    },
+    {
+      "epoch": 6.481481481481482,
+      "grad_norm": 11.754925727844238,
+      "learning_rate": 6.834020335422197e-06,
+      "loss": 0.7778585815429687,
+      "step": 700
+    },
+    {
+      "epoch": 6.481481481481482,
+      "eval_cer": 28.176231196348837,
+      "eval_loss": 1.1462512016296387,
+      "eval_runtime": 176.7618,
+      "eval_samples_per_second": 2.24,
+      "eval_steps_per_second": 0.283,
+      "eval_wer": 59.23022929340197,
+      "step": 700
+    },
+    {
+      "epoch": 6.712962962962963,
+      "grad_norm": 11.707844734191895,
+      "learning_rate": 6.774065417744914e-06,
+      "loss": 0.8317877197265625,
+      "step": 725
+    },
+    {
+      "epoch": 6.944444444444445,
+      "grad_norm": 13.229499816894531,
+      "learning_rate": 6.711814067277222e-06,
+      "loss": 0.8702048492431641,
+      "step": 750
+    },
+    {
+      "epoch": 7.175925925925926,
+      "grad_norm": 9.434710502624512,
+      "learning_rate": 6.647313556820038e-06,
+      "loss": 0.5205693435668945,
+      "step": 775
+    },
+    {
+      "epoch": 7.407407407407407,
+      "grad_norm": 14.408440589904785,
+      "learning_rate": 6.58061286715478e-06,
+      "loss": 0.5769857406616211,
+      "step": 800
+    },
+    {
+      "epoch": 7.407407407407407,
+      "eval_cer": 26.350649992585634,
+      "eval_loss": 1.2063231468200684,
+      "eval_runtime": 174.742,
+      "eval_samples_per_second": 2.266,
+      "eval_steps_per_second": 0.286,
+      "eval_wer": 57.37014506317267,
+      "step": 800
+    },
+    {
+      "epoch": 7.638888888888889,
+      "grad_norm": 10.973855972290039,
+      "learning_rate": 6.5117626498480405e-06,
+      "loss": 0.4379894256591797,
+      "step": 825
+    },
+    {
+      "epoch": 7.87037037037037,
+      "grad_norm": 12.160011291503906,
+      "learning_rate": 6.440815188787503e-06,
+      "loss": 0.5237271118164063,
+      "step": 850
+    },
+    {
+      "epoch": 8.101851851851851,
+      "grad_norm": 11.37704086303711,
+      "learning_rate": 6.367824360478292e-06,
+      "loss": 0.5192337036132812,
+      "step": 875
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 8.334063529968262,
+      "learning_rate": 6.292845593129912e-06,
+      "loss": 0.3543507385253906,
+      "step": 900
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_cer": 28.680407954788855,
+      "eval_loss": 1.2434520721435547,
+      "eval_runtime": 183.3455,
+      "eval_samples_per_second": 2.16,
+      "eval_steps_per_second": 0.273,
+      "eval_wer": 61.12540945250351,
+      "step": 900
+    },
+    {
+      "epoch": 8.564814814814815,
+      "grad_norm": 10.163917541503906,
+      "learning_rate": 6.215935824564843e-06,
+      "loss": 0.3852682876586914,
+      "step": 925
+    },
+    {
+      "epoch": 8.796296296296296,
+      "grad_norm": 9.464524269104004,
+      "learning_rate": 6.137153458980756e-06,
+      "loss": 0.33937496185302735,
+      "step": 950
+    },
+    {
+      "epoch": 9.027777777777779,
+      "grad_norm": 6.08162784576416,
+      "learning_rate": 6.056558322599196e-06,
+      "loss": 0.33474483489990237,
+      "step": 975
+    },
+    {
+      "epoch": 9.25925925925926,
+      "grad_norm": 8.370685577392578,
+      "learning_rate": 5.974211618234372e-06,
+      "loss": 0.23403091430664064,
+      "step": 1000
+    },
+    {
+      "epoch": 9.25925925925926,
+      "eval_cer": 28.210831562124135,
+      "eval_loss": 1.3226666450500488,
+      "eval_runtime": 181.8066,
+      "eval_samples_per_second": 2.178,
+      "eval_steps_per_second": 0.275,
+      "eval_wer": 59.62798315395415,
+      "step": 1000
+    },
+    {
+      "epoch": 9.49074074074074,
+      "grad_norm": 7.153172969818115,
+      "learning_rate": 5.89017587881662e-06,
+      "loss": 0.28863733291625976,
+      "step": 1025
+    },
+    {
+      "epoch": 9.722222222222221,
+      "grad_norm": 11.54667854309082,
+      "learning_rate": 5.8045149199057566e-06,
+      "loss": 0.19027667999267578,
+      "step": 1050
+    },
+    {
+      "epoch": 9.953703703703704,
+      "grad_norm": 11.039658546447754,
+      "learning_rate": 5.717293791230452e-06,
+      "loss": 0.27722286224365233,
+      "step": 1075
+    },
+    {
+      "epoch": 10.185185185185185,
+      "grad_norm": 7.525710105895996,
+      "learning_rate": 5.628578727290372e-06,
+      "loss": 0.14443143844604492,
+      "step": 1100
+    },
+    {
+      "epoch": 10.185185185185185,
+      "eval_cer": 26.02771324534955,
+      "eval_loss": 1.3311429023742676,
+      "eval_runtime": 178.4698,
+      "eval_samples_per_second": 2.219,
+      "eval_steps_per_second": 0.28,
+      "eval_wer": 57.814693495554515,
+      "step": 1100
+    },
+    {
+      "epoch": 10.416666666666666,
+      "grad_norm": 5.609868049621582,
+      "learning_rate": 5.538437097058638e-06,
+      "loss": 0.15044803619384767,
+      "step": 1125
+    },
+    {
+      "epoch": 10.648148148148149,
+      "grad_norm": 11.303506851196289,
+      "learning_rate": 5.446937352822764e-06,
+      "loss": 0.15399362564086913,
+      "step": 1150
+    },
+    {
+      "epoch": 10.87962962962963,
+      "grad_norm": 7.0320258140563965,
+      "learning_rate": 5.354148978202962e-06,
+      "loss": 0.2145862579345703,
+      "step": 1175
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 5.4469122886657715,
+      "learning_rate": 5.2601424353872505e-06,
+      "loss": 0.11755330085754395,
+      "step": 1200
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_cer": 26.51211836620368,
+      "eval_loss": 1.3743336200714111,
+      "eval_runtime": 176.158,
+      "eval_samples_per_second": 2.248,
+      "eval_steps_per_second": 0.284,
+      "eval_wer": 57.6626111371081,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 28,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.002
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 4
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3038919000915968e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30647951d6b5e76b331bc303bcd924bc44b6337b2d17488c183f6c433337b76e
+size 5112

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/config.json

@@ -0,0 +1,49 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "suppress_tokens": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/generation_config.json

@@ -0,0 +1,285 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 50257,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "language": "shona",
+  "length_penalty": 1.0,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "no_timestamps_token_id": 50364,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "target_lookbehind": 10,
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.8.1",
+  "typical_p": 1.0,
+  "use_cache": true
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1275003c81e9f219a3660247da0909de20b39321f740cef91985cfe19cb23ead
+size 6174112552

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6411b6efe25491920102308354e7ca7e2b930ace8d37690e253027e953e39da
+size 12349039011

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b4db095375fab1be860d9036831740eb60a72161e378029ee0d385ba824bcb
+size 14244

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f47c6cfff80e65f9d2aa5bfc07f7a128ace8b9c7b435340d153135eca653d89
+size 1064

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/trainer_state.json

@@ -0,0 +1,537 @@
+{
+  "best_global_step": 800,
+  "best_metric": 57.37014506317267,
+  "best_model_checkpoint": "/home/jupyter-wb344850/chichewa-asr/models/checkpoints/checkpoint-800",
+  "epoch": 12.037037037037036,
+  "eval_steps": 100,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 24.947662353515625,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 11.754910888671875,
+      "step": 25
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 17.93560791015625,
+      "learning_rate": 2.45e-06,
+      "loss": 9.367840576171876,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 20.061756134033203,
+      "learning_rate": 3.7e-06,
+      "loss": 7.043236083984375,
+      "step": 75
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 19.431058883666992,
+      "learning_rate": 4.95e-06,
+      "loss": 6.187430419921875,
+      "step": 100
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "eval_cer": 37.193745571977,
+      "eval_loss": 1.4765740633010864,
+      "eval_runtime": 191.4328,
+      "eval_samples_per_second": 2.069,
+      "eval_steps_per_second": 0.261,
+      "eval_wer": 82.47543284978943,
+      "step": 100
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 16.891460418701172,
+      "learning_rate": 6.2e-06,
+      "loss": 5.158666381835937,
+      "step": 125
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 18.55628776550293,
+      "learning_rate": 7.45e-06,
+      "loss": 4.892176208496093,
+      "step": 150
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 14.085015296936035,
+      "learning_rate": 7.498687774567386e-06,
+      "loss": 4.511752014160156,
+      "step": 175
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 14.737961769104004,
+      "learning_rate": 7.494531126609263e-06,
+      "loss": 4.304852905273438,
+      "step": 200
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "eval_cer": 35.40606000692007,
+      "eval_loss": 1.1418079137802124,
+      "eval_runtime": 203.4432,
+      "eval_samples_per_second": 1.946,
+      "eval_steps_per_second": 0.246,
+      "eval_wer": 74.23958820776791,
+      "step": 200
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 15.683085441589355,
+      "learning_rate": 7.487530934323892e-06,
+      "loss": 3.8006710815429687,
+      "step": 225
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 14.036075592041016,
+      "learning_rate": 7.4776925135589425e-06,
+      "loss": 3.319402160644531,
+      "step": 250
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 14.326029777526855,
+      "learning_rate": 7.465023335472914e-06,
+      "loss": 3.141165771484375,
+      "step": 275
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 14.966941833496094,
+      "learning_rate": 7.449533020861643e-06,
+      "loss": 3.2137042236328126,
+      "step": 300
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "eval_cer": 28.77761850625278,
+      "eval_loss": 1.035639762878418,
+      "eval_runtime": 184.1223,
+      "eval_samples_per_second": 2.151,
+      "eval_steps_per_second": 0.272,
+      "eval_wer": 62.04960224613944,
+      "step": 300
+    },
+    {
+      "epoch": 3.009259259259259,
+      "grad_norm": 11.072875022888184,
+      "learning_rate": 7.431233332852411e-06,
+      "loss": 3.094468688964844,
+      "step": 325
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 14.482994079589844,
+      "learning_rate": 7.41013816797118e-06,
+      "loss": 2.240164794921875,
+      "step": 350
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 14.527769088745117,
+      "learning_rate": 7.386263545589777e-06,
+      "loss": 2.3541885375976563,
+      "step": 375
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 14.758848190307617,
+      "learning_rate": 7.359627595761002e-06,
+      "loss": 2.381937255859375,
+      "step": 400
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "eval_cer": 27.858237358509218,
+      "eval_loss": 1.018039584159851,
+      "eval_runtime": 185.9344,
+      "eval_samples_per_second": 2.13,
+      "eval_steps_per_second": 0.269,
+      "eval_wer": 61.54656059897052,
+      "step": 400
+    },
+    {
+      "epoch": 3.935185185185185,
+      "grad_norm": 13.893526077270508,
+      "learning_rate": 7.330250545450925e-06,
+      "loss": 2.323583068847656,
+      "step": 425
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 12.67662525177002,
+      "learning_rate": 7.298154703178804e-06,
+      "loss": 2.037447052001953,
+      "step": 450
+    },
+    {
+      "epoch": 4.398148148148148,
+      "grad_norm": 13.166596412658691,
+      "learning_rate": 7.263364442076317e-06,
+      "loss": 1.6892933654785156,
+      "step": 475
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 14.612394332885742,
+      "learning_rate": 7.2259061813789465e-06,
+      "loss": 1.7252595520019531,
+      "step": 500
+    },
+    {
+      "epoch": 4.62962962962963,
+      "eval_cer": 29.336167268053977,
+      "eval_loss": 1.0403634309768677,
+      "eval_runtime": 184.8499,
+      "eval_samples_per_second": 2.142,
+      "eval_steps_per_second": 0.27,
+      "eval_wer": 61.49976602714086,
+      "step": 500
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 15.613510131835938,
+      "learning_rate": 7.185808366363582e-06,
+      "loss": 1.6008528137207032,
+      "step": 525
+    },
+    {
+      "epoch": 5.092592592592593,
+      "grad_norm": 14.135201454162598,
+      "learning_rate": 7.143101446747573e-06,
+      "loss": 1.6909564208984376,
+      "step": 550
+    },
+    {
+      "epoch": 5.324074074074074,
+      "grad_norm": 8.78895092010498,
+      "learning_rate": 7.097817853565651e-06,
+      "loss": 1.1801542663574218,
+      "step": 575
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 13.037683486938477,
+      "learning_rate": 7.049991974542245e-06,
+      "loss": 1.2334317779541015,
+      "step": 600
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_cer": 27.09538167498723,
+      "eval_loss": 1.1000748872756958,
+      "eval_runtime": 179.2605,
+      "eval_samples_per_second": 2.209,
+      "eval_steps_per_second": 0.279,
+      "eval_wer": 57.99017313991577,
+      "step": 600
+    },
+    {
+      "epoch": 5.787037037037037,
+      "grad_norm": 11.986921310424805,
+      "learning_rate": 6.999660127977939e-06,
+      "loss": 1.087800521850586,
+      "step": 625
+    },
+    {
+      "epoch": 6.018518518518518,
+      "grad_norm": 9.024539947509766,
+      "learning_rate": 6.9468605351698555e-06,
+      "loss": 1.152771224975586,
+      "step": 650
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 10.050127983093262,
+      "learning_rate": 6.891633291386944e-06,
+      "loss": 0.7668762969970703,
+      "step": 675
+    },
+    {
+      "epoch": 6.481481481481482,
+      "grad_norm": 11.754925727844238,
+      "learning_rate": 6.834020335422197e-06,
+      "loss": 0.7778585815429687,
+      "step": 700
+    },
+    {
+      "epoch": 6.481481481481482,
+      "eval_cer": 28.176231196348837,
+      "eval_loss": 1.1462512016296387,
+      "eval_runtime": 176.7618,
+      "eval_samples_per_second": 2.24,
+      "eval_steps_per_second": 0.283,
+      "eval_wer": 59.23022929340197,
+      "step": 700
+    },
+    {
+      "epoch": 6.712962962962963,
+      "grad_norm": 11.707844734191895,
+      "learning_rate": 6.774065417744914e-06,
+      "loss": 0.8317877197265625,
+      "step": 725
+    },
+    {
+      "epoch": 6.944444444444445,
+      "grad_norm": 13.229499816894531,
+      "learning_rate": 6.711814067277222e-06,
+      "loss": 0.8702048492431641,
+      "step": 750
+    },
+    {
+      "epoch": 7.175925925925926,
+      "grad_norm": 9.434710502624512,
+      "learning_rate": 6.647313556820038e-06,
+      "loss": 0.5205693435668945,
+      "step": 775
+    },
+    {
+      "epoch": 7.407407407407407,
+      "grad_norm": 14.408440589904785,
+      "learning_rate": 6.58061286715478e-06,
+      "loss": 0.5769857406616211,
+      "step": 800
+    },
+    {
+      "epoch": 7.407407407407407,
+      "eval_cer": 26.350649992585634,
+      "eval_loss": 1.2063231468200684,
+      "eval_runtime": 174.742,
+      "eval_samples_per_second": 2.266,
+      "eval_steps_per_second": 0.286,
+      "eval_wer": 57.37014506317267,
+      "step": 800
+    },
+    {
+      "epoch": 7.638888888888889,
+      "grad_norm": 10.973855972290039,
+      "learning_rate": 6.5117626498480405e-06,
+      "loss": 0.4379894256591797,
+      "step": 825
+    },
+    {
+      "epoch": 7.87037037037037,
+      "grad_norm": 12.160011291503906,
+      "learning_rate": 6.440815188787503e-06,
+      "loss": 0.5237271118164063,
+      "step": 850
+    },
+    {
+      "epoch": 8.101851851851851,
+      "grad_norm": 11.37704086303711,
+      "learning_rate": 6.367824360478292e-06,
+      "loss": 0.5192337036132812,
+      "step": 875
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 8.334063529968262,
+      "learning_rate": 6.292845593129912e-06,
+      "loss": 0.3543507385253906,
+      "step": 900
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_cer": 28.680407954788855,
+      "eval_loss": 1.2434520721435547,
+      "eval_runtime": 183.3455,
+      "eval_samples_per_second": 2.16,
+      "eval_steps_per_second": 0.273,
+      "eval_wer": 61.12540945250351,
+      "step": 900
+    },
+    {
+      "epoch": 8.564814814814815,
+      "grad_norm": 10.163917541503906,
+      "learning_rate": 6.215935824564843e-06,
+      "loss": 0.3852682876586914,
+      "step": 925
+    },
+    {
+      "epoch": 8.796296296296296,
+      "grad_norm": 9.464524269104004,
+      "learning_rate": 6.137153458980756e-06,
+      "loss": 0.33937496185302735,
+      "step": 950
+    },
+    {
+      "epoch": 9.027777777777779,
+      "grad_norm": 6.08162784576416,
+      "learning_rate": 6.056558322599196e-06,
+      "loss": 0.33474483489990237,
+      "step": 975
+    },
+    {
+      "epoch": 9.25925925925926,
+      "grad_norm": 8.370685577392578,
+      "learning_rate": 5.974211618234372e-06,
+      "loss": 0.23403091430664064,
+      "step": 1000
+    },
+    {
+      "epoch": 9.25925925925926,
+      "eval_cer": 28.210831562124135,
+      "eval_loss": 1.3226666450500488,
+      "eval_runtime": 181.8066,
+      "eval_samples_per_second": 2.178,
+      "eval_steps_per_second": 0.275,
+      "eval_wer": 59.62798315395415,
+      "step": 1000
+    },
+    {
+      "epoch": 9.49074074074074,
+      "grad_norm": 7.153172969818115,
+      "learning_rate": 5.89017587881662e-06,
+      "loss": 0.28863733291625976,
+      "step": 1025
+    },
+    {
+      "epoch": 9.722222222222221,
+      "grad_norm": 11.54667854309082,
+      "learning_rate": 5.8045149199057566e-06,
+      "loss": 0.19027667999267578,
+      "step": 1050
+    },
+    {
+      "epoch": 9.953703703703704,
+      "grad_norm": 11.039658546447754,
+      "learning_rate": 5.717293791230452e-06,
+      "loss": 0.27722286224365233,
+      "step": 1075
+    },
+    {
+      "epoch": 10.185185185185185,
+      "grad_norm": 7.525710105895996,
+      "learning_rate": 5.628578727290372e-06,
+      "loss": 0.14443143844604492,
+      "step": 1100
+    },
+    {
+      "epoch": 10.185185185185185,
+      "eval_cer": 26.02771324534955,
+      "eval_loss": 1.3311429023742676,
+      "eval_runtime": 178.4698,
+      "eval_samples_per_second": 2.219,
+      "eval_steps_per_second": 0.28,
+      "eval_wer": 57.814693495554515,
+      "step": 1100
+    },
+    {
+      "epoch": 10.416666666666666,
+      "grad_norm": 5.609868049621582,
+      "learning_rate": 5.538437097058638e-06,
+      "loss": 0.15044803619384767,
+      "step": 1125
+    },
+    {
+      "epoch": 10.648148148148149,
+      "grad_norm": 11.303506851196289,
+      "learning_rate": 5.446937352822764e-06,
+      "loss": 0.15399362564086913,
+      "step": 1150
+    },
+    {
+      "epoch": 10.87962962962963,
+      "grad_norm": 7.0320258140563965,
+      "learning_rate": 5.354148978202962e-06,
+      "loss": 0.2145862579345703,
+      "step": 1175
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 5.4469122886657715,
+      "learning_rate": 5.2601424353872505e-06,
+      "loss": 0.11755330085754395,
+      "step": 1200
+    },
+    {
+      "epoch": 11.11111111111111,
+      "eval_cer": 26.51211836620368,
+      "eval_loss": 1.3743336200714111,
+      "eval_runtime": 176.158,
+      "eval_samples_per_second": 2.248,
+      "eval_steps_per_second": 0.284,
+      "eval_wer": 57.6626111371081,
+      "step": 1200
+    },
+    {
+      "epoch": 11.342592592592593,
+      "grad_norm": 6.336820602416992,
+      "learning_rate": 5.16498911162346e-06,
+      "loss": 0.13985513687133788,
+      "step": 1225
+    },
+    {
+      "epoch": 11.574074074074074,
+      "grad_norm": 4.456954479217529,
+      "learning_rate": 5.068761265008761e-06,
+      "loss": 0.11695966720581055,
+      "step": 1250
+    },
+    {
+      "epoch": 11.805555555555555,
+      "grad_norm": 5.237090587615967,
+      "learning_rate": 4.9715319696178826e-06,
+      "loss": 0.09781095504760742,
+      "step": 1275
+    },
+    {
+      "epoch": 12.037037037037036,
+      "grad_norm": 3.9604368209838867,
+      "learning_rate": 4.873375060011682e-06,
+      "loss": 0.1288002586364746,
+      "step": 1300
+    },
+    {
+      "epoch": 12.037037037037036,
+      "eval_cer": 28.138335557642563,
+      "eval_loss": 1.3983486890792847,
+      "eval_runtime": 182.25,
+      "eval_samples_per_second": 2.173,
+      "eval_steps_per_second": 0.274,
+      "eval_wer": 59.300421151146466,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 28,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.002
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 5
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4125438959353856e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-1300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30647951d6b5e76b331bc303bcd924bc44b6337b2d17488c183f6c433337b76e
+size 5112

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/config.json

@@ -0,0 +1,49 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "suppress_tokens": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/generation_config.json

@@ -0,0 +1,285 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 50257,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "language": "shona",
+  "length_penalty": 1.0,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "no_timestamps_token_id": 50364,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "target_lookbehind": 10,
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.8.1",
+  "typical_p": 1.0,
+  "use_cache": true
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e320f93cb15f71a4280e54d92e1974d7a5784768e6d5f19e86429cb656643e
+size 6174112552

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5fc0b097f1ffb088e7fa4c3761c2ccaf8f18e2e78959f320189b8e031e72e1
+size 12349039011

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc6889957499e0c886c03f87f77b07dae02807a4a830665de3ad4499c9c6208
+size 14244

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708a6fd17994d3c421c8b6b31bac6a3b7d3952e1b259f727bb5f72cb0824edad
+size 1064

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/trainer_state.json

@@ -0,0 +1,347 @@
+{
+  "best_global_step": 800,
+  "best_metric": 57.37014506317267,
+  "best_model_checkpoint": "/home/jupyter-wb344850/chichewa-asr/models/checkpoints/checkpoint-800",
+  "epoch": 7.407407407407407,
+  "eval_steps": 100,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 24.947662353515625,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 11.754910888671875,
+      "step": 25
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 17.93560791015625,
+      "learning_rate": 2.45e-06,
+      "loss": 9.367840576171876,
+      "step": 50
+    },
+    {
+      "epoch": 0.6944444444444444,
+      "grad_norm": 20.061756134033203,
+      "learning_rate": 3.7e-06,
+      "loss": 7.043236083984375,
+      "step": 75
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 19.431058883666992,
+      "learning_rate": 4.95e-06,
+      "loss": 6.187430419921875,
+      "step": 100
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "eval_cer": 37.193745571977,
+      "eval_loss": 1.4765740633010864,
+      "eval_runtime": 191.4328,
+      "eval_samples_per_second": 2.069,
+      "eval_steps_per_second": 0.261,
+      "eval_wer": 82.47543284978943,
+      "step": 100
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 16.891460418701172,
+      "learning_rate": 6.2e-06,
+      "loss": 5.158666381835937,
+      "step": 125
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 18.55628776550293,
+      "learning_rate": 7.45e-06,
+      "loss": 4.892176208496093,
+      "step": 150
+    },
+    {
+      "epoch": 1.6203703703703702,
+      "grad_norm": 14.085015296936035,
+      "learning_rate": 7.498687774567386e-06,
+      "loss": 4.511752014160156,
+      "step": 175
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 14.737961769104004,
+      "learning_rate": 7.494531126609263e-06,
+      "loss": 4.304852905273438,
+      "step": 200
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "eval_cer": 35.40606000692007,
+      "eval_loss": 1.1418079137802124,
+      "eval_runtime": 203.4432,
+      "eval_samples_per_second": 1.946,
+      "eval_steps_per_second": 0.246,
+      "eval_wer": 74.23958820776791,
+      "step": 200
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 15.683085441589355,
+      "learning_rate": 7.487530934323892e-06,
+      "loss": 3.8006710815429687,
+      "step": 225
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 14.036075592041016,
+      "learning_rate": 7.4776925135589425e-06,
+      "loss": 3.319402160644531,
+      "step": 250
+    },
+    {
+      "epoch": 2.5462962962962963,
+      "grad_norm": 14.326029777526855,
+      "learning_rate": 7.465023335472914e-06,
+      "loss": 3.141165771484375,
+      "step": 275
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 14.966941833496094,
+      "learning_rate": 7.449533020861643e-06,
+      "loss": 3.2137042236328126,
+      "step": 300
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "eval_cer": 28.77761850625278,
+      "eval_loss": 1.035639762878418,
+      "eval_runtime": 184.1223,
+      "eval_samples_per_second": 2.151,
+      "eval_steps_per_second": 0.272,
+      "eval_wer": 62.04960224613944,
+      "step": 300
+    },
+    {
+      "epoch": 3.009259259259259,
+      "grad_norm": 11.072875022888184,
+      "learning_rate": 7.431233332852411e-06,
+      "loss": 3.094468688964844,
+      "step": 325
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 14.482994079589844,
+      "learning_rate": 7.41013816797118e-06,
+      "loss": 2.240164794921875,
+      "step": 350
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 14.527769088745117,
+      "learning_rate": 7.386263545589777e-06,
+      "loss": 2.3541885375976563,
+      "step": 375
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 14.758848190307617,
+      "learning_rate": 7.359627595761002e-06,
+      "loss": 2.381937255859375,
+      "step": 400
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "eval_cer": 27.858237358509218,
+      "eval_loss": 1.018039584159851,
+      "eval_runtime": 185.9344,
+      "eval_samples_per_second": 2.13,
+      "eval_steps_per_second": 0.269,
+      "eval_wer": 61.54656059897052,
+      "step": 400
+    },
+    {
+      "epoch": 3.935185185185185,
+      "grad_norm": 13.893526077270508,
+      "learning_rate": 7.330250545450925e-06,
+      "loss": 2.323583068847656,
+      "step": 425
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 12.67662525177002,
+      "learning_rate": 7.298154703178804e-06,
+      "loss": 2.037447052001953,
+      "step": 450
+    },
+    {
+      "epoch": 4.398148148148148,
+      "grad_norm": 13.166596412658691,
+      "learning_rate": 7.263364442076317e-06,
+      "loss": 1.6892933654785156,
+      "step": 475
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 14.612394332885742,
+      "learning_rate": 7.2259061813789465e-06,
+      "loss": 1.7252595520019531,
+      "step": 500
+    },
+    {
+      "epoch": 4.62962962962963,
+      "eval_cer": 29.336167268053977,
+      "eval_loss": 1.0403634309768677,
+      "eval_runtime": 184.8499,
+      "eval_samples_per_second": 2.142,
+      "eval_steps_per_second": 0.27,
+      "eval_wer": 61.49976602714086,
+      "step": 500
+    },
+    {
+      "epoch": 4.861111111111111,
+      "grad_norm": 15.613510131835938,
+      "learning_rate": 7.185808366363582e-06,
+      "loss": 1.6008528137207032,
+      "step": 525
+    },
+    {
+      "epoch": 5.092592592592593,
+      "grad_norm": 14.135201454162598,
+      "learning_rate": 7.143101446747573e-06,
+      "loss": 1.6909564208984376,
+      "step": 550
+    },
+    {
+      "epoch": 5.324074074074074,
+      "grad_norm": 8.78895092010498,
+      "learning_rate": 7.097817853565651e-06,
+      "loss": 1.1801542663574218,
+      "step": 575
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 13.037683486938477,
+      "learning_rate": 7.049991974542245e-06,
+      "loss": 1.2334317779541015,
+      "step": 600
+    },
+    {
+      "epoch": 5.555555555555555,
+      "eval_cer": 27.09538167498723,
+      "eval_loss": 1.1000748872756958,
+      "eval_runtime": 179.2605,
+      "eval_samples_per_second": 2.209,
+      "eval_steps_per_second": 0.279,
+      "eval_wer": 57.99017313991577,
+      "step": 600
+    },
+    {
+      "epoch": 5.787037037037037,
+      "grad_norm": 11.986921310424805,
+      "learning_rate": 6.999660127977939e-06,
+      "loss": 1.087800521850586,
+      "step": 625
+    },
+    {
+      "epoch": 6.018518518518518,
+      "grad_norm": 9.024539947509766,
+      "learning_rate": 6.9468605351698555e-06,
+      "loss": 1.152771224975586,
+      "step": 650
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 10.050127983093262,
+      "learning_rate": 6.891633291386944e-06,
+      "loss": 0.7668762969970703,
+      "step": 675
+    },
+    {
+      "epoch": 6.481481481481482,
+      "grad_norm": 11.754925727844238,
+      "learning_rate": 6.834020335422197e-06,
+      "loss": 0.7778585815429687,
+      "step": 700
+    },
+    {
+      "epoch": 6.481481481481482,
+      "eval_cer": 28.176231196348837,
+      "eval_loss": 1.1462512016296387,
+      "eval_runtime": 176.7618,
+      "eval_samples_per_second": 2.24,
+      "eval_steps_per_second": 0.283,
+      "eval_wer": 59.23022929340197,
+      "step": 700
+    },
+    {
+      "epoch": 6.712962962962963,
+      "grad_norm": 11.707844734191895,
+      "learning_rate": 6.774065417744914e-06,
+      "loss": 0.8317877197265625,
+      "step": 725
+    },
+    {
+      "epoch": 6.944444444444445,
+      "grad_norm": 13.229499816894531,
+      "learning_rate": 6.711814067277222e-06,
+      "loss": 0.8702048492431641,
+      "step": 750
+    },
+    {
+      "epoch": 7.175925925925926,
+      "grad_norm": 9.434710502624512,
+      "learning_rate": 6.647313556820038e-06,
+      "loss": 0.5205693435668945,
+      "step": 775
+    },
+    {
+      "epoch": 7.407407407407407,
+      "grad_norm": 14.408440589904785,
+      "learning_rate": 6.58061286715478e-06,
+      "loss": 0.5769857406616211,
+      "step": 800
+    },
+    {
+      "epoch": 7.407407407407407,
+      "eval_cer": 26.350649992585634,
+      "eval_loss": 1.2063231468200684,
+      "eval_runtime": 174.742,
+      "eval_samples_per_second": 2.266,
+      "eval_steps_per_second": 0.286,
+      "eval_wer": 57.37014506317267,
+      "step": 800
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 28,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.002
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.692839167164416e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

whisper-large-v3-chichewa-14h-normalized-transcript/checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30647951d6b5e76b331bc303bcd924bc44b6337b2d17488c183f6c433337b76e
+size 5112

whisper-large-v3-chichewa-14h-normalized-transcript/config.json

@@ -0,0 +1,49 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "suppress_tokens": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

whisper-large-v3-chichewa-14h-normalized-transcript/generation_config.json

@@ -0,0 +1,285 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 50257,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "forced_decoder_ids": null,
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "language": "shona",
+  "length_penalty": 1.0,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "no_timestamps_token_id": 50364,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "target_lookbehind": 10,
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.8.1",
+  "typical_p": 1.0,
+  "use_cache": true
+}

whisper-large-v3-chichewa-14h-normalized-transcript/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e320f93cb15f71a4280e54d92e1974d7a5784768e6d5f19e86429cb656643e
+size 6174112552

whisper-large-v3-chichewa-14h-normalized-transcript/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

whisper-large-v3-chichewa-14h-normalized-transcript/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30647951d6b5e76b331bc303bcd924bc44b6337b2d17488c183f6c433337b76e
+size 5112