Init

Browse files

Files changed (10) hide show

.gitattributes +1 -0
added_tokens.json +4 -0
config.json +82 -0
language_model/lm.binary +3 -0
language_model/unigrams.txt +0 -0
model.safetensors +3 -0
preprocessor_config.json +11 -0
special_tokens_map.json +6 -0
tokenizer_config.json +48 -0
vocab.json +40 -0

.gitattributes CHANGED Viewed

@@ -1,6 +1,7 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text

 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.binary filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "</s>": 39,
+  "<s>": 38
+}

config.json ADDED Viewed

	@@ -0,0 +1,82 @@

+{
+  "_name_or_path": "facebook/w2v-bert-2.0",
+  "activation_dropout": 0.05,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.0,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 2,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.37.0",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 40,
+  "xvector_output_dim": 512
+}

language_model/lm.binary ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff37f030c7e76538548010ef6fc13245b7cbe3aa198f5e3bc2e4faa6a5c3135
+size 881279204

language_model/unigrams.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4e48f4434356a769f2d5475a93de24352072e89dc5996b5c29ee281cb64a57
+size 2422978560

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

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 +1,48 @@

+{
+  "added_tokens_decoder": {
+    "2": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "'": 0,
+  "-": 1,
+  "<pad>": 2,
+  "<unk>": 3,
+  "|": 4,
+  "а": 5,
+  "б": 6,
+  "в": 7,
+  "г": 8,
+  "д": 9,
+  "е": 10,
+  "ж": 11,
+  "з": 12,
+  "и": 13,
+  "й": 14,
+  "к": 15,
+  "л": 16,
+  "м": 17,
+  "н": 18,
+  "о": 19,
+  "п": 20,
+  "р": 21,
+  "с": 22,
+  "т": 23,
+  "у": 24,
+  "ф": 25,
+  "х": 26,
+  "ц": 27,
+  "ч": 28,
+  "ш": 29,
+  "щ": 30,
+  "ь": 31,
+  "ю": 32,
+  "я": 33,
+  "є": 34,
+  "і": 35,
+  "ї": 36,
+  "ґ": 37
+}