Upload folder using huggingface_hub

config.json

@@ -0,0 +1,46 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "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_hidden_layers": 4,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

generation_config.json

@@ -0,0 +1,241 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      2
+    ],
+    [
+      3,
+      0
+    ],
+    [
+      3,
+      2
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      4
+    ],
+    [
+      3,
+      5
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": [
+    50257
+  ],
+  "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,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
+  "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,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7024926f2124fcb40907f91584f20990731f7273387e65006e9d3e6953fc2b9
+size 151061672

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23514630188c39afda4d4f4cc24cb91b7964791b29289eade3ac7807e4999ef
+size 302220811

processor_config.json

@@ -0,0 +1,17 @@
+{
+  "feature_extractor": {
+    "chunk_length": 30,
+    "dither": 0.0,
+    "feature_extractor_type": "WhisperFeatureExtractor",
+    "feature_size": 80,
+    "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
+  },
+  "processor_class": "WhisperProcessor"
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:039970b6882c953a4975fc4dfcb09d0a09918844f38de8373269a68c0dfa9305
+size 14455

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16c63c5cfdc9a7ee451fba1e6666f4cc178e3589a9ce9b2d4f69bdcbda86e79
+size 1465

tokenizer_config.json

@@ -0,0 +1,127 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "is_local": false,
+  "language": "french",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "predict_timestamps": false,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "task": "translate",
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,254 @@
+{
+  "best_global_step": 500,
+  "best_metric": 2.7007479667663574,
+  "best_model_checkpoint": "Mazzy-whisper-tiny\\checkpoint-500",
+  "epoch": 0.625,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03125,
+      "grad_norm": 75.82250213623047,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 4.257205200195313,
+      "step": 25
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 91.59275817871094,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 3.810027770996094,
+      "step": 50
+    },
+    {
+      "epoch": 0.0625,
+      "eval_loss": 3.387531042098999,
+      "eval_runtime": 56.07,
+      "eval_samples_per_second": 1.783,
+      "eval_steps_per_second": 1.783,
+      "step": 50
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 109.6454086303711,
+      "learning_rate": 9.466666666666667e-06,
+      "loss": 3.426136169433594,
+      "step": 75
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 77.40877532958984,
+      "learning_rate": 8.91111111111111e-06,
+      "loss": 3.1471734619140626,
+      "step": 100
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 3.086820602416992,
+      "eval_runtime": 55.5379,
+      "eval_samples_per_second": 1.801,
+      "eval_steps_per_second": 1.801,
+      "step": 100
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 65.8832015991211,
+      "learning_rate": 8.355555555555556e-06,
+      "loss": 2.979889221191406,
+      "step": 125
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 97.50338745117188,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 3.0117352294921873,
+      "step": 150
+    },
+    {
+      "epoch": 0.1875,
+      "eval_loss": 2.8795320987701416,
+      "eval_runtime": 56.4467,
+      "eval_samples_per_second": 1.772,
+      "eval_steps_per_second": 1.772,
+      "step": 150
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 63.26200866699219,
+      "learning_rate": 7.244444444444445e-06,
+      "loss": 2.979839172363281,
+      "step": 175
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 56.74595642089844,
+      "learning_rate": 6.688888888888889e-06,
+      "loss": 2.9879776000976563,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 2.8465237617492676,
+      "eval_runtime": 76.306,
+      "eval_samples_per_second": 1.311,
+      "eval_steps_per_second": 1.311,
+      "step": 200
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 96.1812515258789,
+      "learning_rate": 6.133333333333334e-06,
+      "loss": 2.7666366577148436,
+      "step": 225
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 71.51004791259766,
+      "learning_rate": 5.577777777777778e-06,
+      "loss": 2.8252435302734376,
+      "step": 250
+    },
+    {
+      "epoch": 0.3125,
+      "eval_loss": 2.7943179607391357,
+      "eval_runtime": 1293.0599,
+      "eval_samples_per_second": 0.077,
+      "eval_steps_per_second": 0.077,
+      "step": 250
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 98.3506088256836,
+      "learning_rate": 5.022222222222223e-06,
+      "loss": 2.8509982299804686,
+      "step": 275
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 76.27555847167969,
+      "learning_rate": 4.4666666666666665e-06,
+      "loss": 2.8936077880859377,
+      "step": 300
+    },
+    {
+      "epoch": 0.375,
+      "eval_loss": 2.7515389919281006,
+      "eval_runtime": 247.7616,
+      "eval_samples_per_second": 0.404,
+      "eval_steps_per_second": 0.404,
+      "step": 300
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 115.49108123779297,
+      "learning_rate": 3.911111111111112e-06,
+      "loss": 2.7140411376953124,
+      "step": 325
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 62.67667007446289,
+      "learning_rate": 3.3555555555555557e-06,
+      "loss": 2.800578308105469,
+      "step": 350
+    },
+    {
+      "epoch": 0.4375,
+      "eval_loss": 2.7254576683044434,
+      "eval_runtime": 52.2594,
+      "eval_samples_per_second": 1.914,
+      "eval_steps_per_second": 1.914,
+      "step": 350
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 53.711524963378906,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 2.7111419677734374,
+      "step": 375
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 55.54822540283203,
+      "learning_rate": 2.2444444444444445e-06,
+      "loss": 2.8701107788085936,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.7176525592803955,
+      "eval_runtime": 55.6682,
+      "eval_samples_per_second": 1.796,
+      "eval_steps_per_second": 1.796,
+      "step": 400
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 106.42744445800781,
+      "learning_rate": 1.688888888888889e-06,
+      "loss": 2.784833984375,
+      "step": 425
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 55.58470153808594,
+      "learning_rate": 1.1333333333333334e-06,
+      "loss": 2.8060418701171876,
+      "step": 450
+    },
+    {
+      "epoch": 0.5625,
+      "eval_loss": 2.7064270973205566,
+      "eval_runtime": 76.5646,
+      "eval_samples_per_second": 1.306,
+      "eval_steps_per_second": 1.306,
+      "step": 450
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 49.802032470703125,
+      "learning_rate": 5.777777777777778e-07,
+      "loss": 2.7749835205078126,
+      "step": 475
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 69.92212677001953,
+      "learning_rate": 2.2222222222222224e-08,
+      "loss": 2.775958251953125,
+      "step": 500
+    },
+    {
+      "epoch": 0.625,
+      "eval_loss": 2.7007479667663574,
+      "eval_runtime": 53.3461,
+      "eval_samples_per_second": 1.875,
+      "eval_steps_per_second": 1.875,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.230944256e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4827c7e5dee97d95625fff6cd366043a4c3dfbe65cbe0a8812baa00c4a50c05c
+size 5393