Initial commit for wav2vec2-xls-r-300m pronunciation model

Browse files

Files changed (6) hide show

config.json +109 -0
model.safetensors +3 -0
preprocessor_config.json +10 -0
special_tokens_map.json +6 -0
tokenizer_config.json +50 -0
vocab.json +84 -0

config.json ADDED Viewed

	@@ -0,0 +1,109 @@

+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 0.075,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 79,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 84,
+  "xvector_output_dim": 512
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d4d56b7436c37080404b86bfa0f88d22e2c9d03cb7d6c7ab81d65fe2ad73f0
+size 1262151880

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,50 @@

+{
+  "added_tokens_decoder": {
+    "79": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "80": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "82": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "83": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_phonemize": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "phone_delimiter_token": " ",
+  "phonemizer_backend": "espeak",
+  "phonemizer_lang": "en-us",
+  "processor_class": "Wav2Vec2Processor",
+  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": null
+}

vocab.json ADDED Viewed

	@@ -0,0 +1,84 @@

+{
+  "<pad>": 79,
+  "<unk>": 80,
+  "|": 81,
+  "ᄀ": 0,
+  "ᄂ": 1,
+  "ᄃ": 2,
+  "ᄄ": 3,
+  "ᄅ": 4,
+  "ᄆ": 5,
+  "ᄇ": 6,
+  "ᄈ": 7,
+  "ᄉ": 8,
+  "ᄊ": 9,
+  "ᄌ": 10,
+  "ᄍ": 11,
+  "ᄏ": 12,
+  "ᄑ": 13,
+  "ᄒ": 14,
+  "ᅡ": 15,
+  "ᅢ": 16,
+  "ᅥ": 17,
+  "ᅦ": 18,
+  "ᅧ": 19,
+  "ᅩ": 20,
+  "ᅫ": 21,
+  "ᅭ": 22,
+  "ᅮ": 23,
+  "ᅯ": 24,
+  "ᅱ": 25,
+  "ᅳ": 26,
+  "ᅵ": 27,
+  "ᆨ": 28,
+  "ᆫ": 29,
+  "ᆮ": 30,
+  "ᆯ": 31,
+  "ᆷ": 32,
+  "ᆸ": 33,
+  "ㄱ": 34,
+  "ㄲ": 35,
+  "ㄴ": 36,
+  "ㄵ": 37,
+  "ㄷ": 38,
+  "ㄸ": 39,
+  "ㄹ": 40,
+  "ㄺ": 41,
+  "ㄻ": 42,
+  "ㄼ": 43,
+  "ㅁ": 44,
+  "ㅂ": 45,
+  "ㅃ": 46,
+  "ㅄ": 47,
+  "ㅅ": 48,
+  "ㅆ": 49,
+  "ㅇ": 50,
+  "ㅈ": 51,
+  "ㅉ": 52,
+  "ㅊ": 53,
+  "ㅋ": 54,
+  "ㅌ": 55,
+  "ㅍ": 56,
+  "ㅎ": 57,
+  "ㅏ": 58,
+  "ㅐ": 59,
+  "ㅑ": 60,
+  "ㅒ": 61,
+  "ㅓ": 62,
+  "ㅔ": 63,
+  "ㅕ": 64,
+  "ㅖ": 65,
+  "ㅗ": 66,
+  "ㅘ": 67,
+  "ㅙ": 68,
+  "ㅚ": 69,
+  "ㅛ": 70,
+  "ㅜ": 71,
+  "ㅝ": 72,
+  "ㅞ": 73,
+  "ㅟ": 74,
+  "ㅠ": 75,
+  "ㅡ": 76,
+  "ㅢ": 77,
+  "ㅣ": 78
+}