Init

Browse files

Files changed (14) hide show

.gitattributes +1 -0
README.md +0 -3
added_tokens.json +4 -0
alphabet.json +1 -0
config.json +108 -0
language_model/5gram_correct.arpa +3 -0
language_model/attrs.json +1 -0
language_model/unigrams.txt +0 -0
preprocessor_config.json +10 -0
pytorch_model.bin +3 -0
special_tokens_map.json +22 -0
tokenizer_config.json +13 -0
trainer_state.json +0 -0
vocab.json +40 -0

.gitattributes CHANGED Viewed

@@ -1,4 +1,5 @@
 *.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

 *.7z filter=lfs diff=lfs merge=lfs -text
+*.arpa 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

README.md DELETED Viewed

@@ -1,3 +0,0 @@
----
-license: apache-2.0
----

added_tokens.json ADDED Viewed

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

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

alphabet.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"labels": ["'", "-", "", "\u2047", " ", "\u0430", "\u0431", "\u0432", "\u0433", "\u0434", "\u0435", "\u0436", "\u0437", "\u0438", "\u0439", "\u043a", "\u043b", "\u043c", "\u043d", "\u043e", "\u043f", "\u0440", "\u0441", "\u0442", "\u0443", "\u0444", "\u0445", "\u0446", "\u0447", "\u0448", "\u0449", "\u044c", "\u044e", "\u044f", "\u0454", "\u0456", "\u0457", "\u0491", "<s>", "</s>"], "is_bpe": false}

config.json ADDED Viewed

	@@ -0,0 +1,108 @@

+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.04,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "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": 2,
+  "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": "4.20.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 40,
+  "xvector_output_dim": 512
+}

language_model/5gram_correct.arpa ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6ecaf19ebaf6058c8b9cebdcede93014168931a6cb3638ef507586124afd786e
+size 31985659

language_model/attrs.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/unigrams.txt ADDED Viewed

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

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
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:c792784e58b0c6291e8f7fda8e368f28cae8e77eccb692c7f34c6f7d04f833bd
+size 1262062705

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

trainer_state.json ADDED Viewed

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

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
+}