Initial commit for wav2vec2-large-robust pronunciation model

Browse files

Files changed (6) hide show

config.json +110 -0
model.safetensors +3 -0
preprocessor_config.json +10 -0
special_tokens_map.json +6 -0
tokenizer_config.json +49 -0
vocab.json +93 -0

config.json ADDED Viewed

	@@ -0,0 +1,110 @@

+{
+  "_name_or_path": "facebook/wav2vec2-large-robust",
+  "activation_dropout": 0.1,
+  "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": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 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": 0.05,
+  "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": 89,
+  "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": "4.39.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 93,
+  "xvector_output_dim": 512
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:53774daf48d7442147100028a4d33050350ff6fdda0abbefab54f43fc9ce5633
+size 1262188780

preprocessor_config.json ADDED Viewed

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

+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "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 +1,49 @@

+{
+  "added_tokens_decoder": {
+    "89": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "90": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "91": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "92": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_phonemize": false,
+  "eos_token": "</s>",
+  "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 +1,93 @@

+{
+  "<pad>": 89,
+  "<unk>": 90,
+  "aa": 0,
+  "aa_err": 1,
+  "ae": 2,
+  "ae_err": 3,
+  "ah": 4,
+  "ah_err": 5,
+  "ao": 6,
+  "ao_err": 7,
+  "aw": 8,
+  "aw_err": 9,
+  "ax": 10,
+  "ax_err": 11,
+  "ay": 12,
+  "ay_err": 13,
+  "b": 14,
+  "b*": 15,
+  "b_err": 16,
+  "ch": 17,
+  "ch_err": 18,
+  "d": 19,
+  "d*": 20,
+  "d_err": 21,
+  "dh": 22,
+  "dh_err": 23,
+  "eh": 24,
+  "eh_err": 25,
+  "er": 26,
+  "er_err": 27,
+  "eu": 28,
+  "eu_err": 29,
+  "ey": 30,
+  "ey_err": 31,
+  "f": 32,
+  "f_err": 33,
+  "g": 34,
+  "g*": 35,
+  "g_err": 36,
+  "hh": 37,
+  "hh_err": 38,
+  "ih": 39,
+  "ih_err": 40,
+  "iy": 41,
+  "iy_err": 42,
+  "jh": 43,
+  "jh_err": 44,
+  "k": 45,
+  "k_err": 46,
+  "l": 47,
+  "l_err": 48,
+  "m": 49,
+  "m_err": 50,
+  "n": 51,
+  "n_err": 52,
+  "ng": 53,
+  "ng_err": 54,
+  "o": 55,
+  "o_err": 56,
+  "ow": 57,
+  "ow_err": 58,
+  "oy": 59,
+  "oy_err": 60,
+  "p": 61,
+  "p_err": 62,
+  "r": 63,
+  "r_err": 64,
+  "s": 65,
+  "s_err": 66,
+  "sh": 67,
+  "sh_err": 68,
+  "t": 69,
+  "t_err": 70,
+  "th": 71,
+  "th_err": 72,
+  "ts": 73,
+  "ts_err": 74,
+  "uh": 75,
+  "uh_err": 76,
+  "uw": 77,
+  "uw_err": 78,
+  "v": 79,
+  "v_err": 80,
+  "w": 81,
+  "w_err": 82,
+  "y": 83,
+  "y_err": 84,
+  "z": 85,
+  "z_err": 86,
+  "zh": 87,
+  "zh_err": 88
+}