Wav2Vec Malayalam with SMC Ngrams CTCDecode

Browse files

Files changed (14) hide show

.gitattributes +14 -27
added_tokens.json +4 -0
alphabet.json +1 -0
config.json +116 -0
flax_model.msgpack +3 -0
language_model/5gram.bin +3 -0
language_model/attrs.json +1 -0
language_model/unigrams.txt +0 -0
model.safetensors +3 -0
preprocessor_config.json +10 -0
pytorch_model.bin +3 -0
special_tokens_map.json +6 -0
tokenizer_config.json +48 -0
vocab.json +78 -0

.gitattributes CHANGED Viewed

@@ -1,35 +1,22 @@
-*.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
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text
+language_model/5gram.bin filter=lfs diff=lfs merge=lfs -text
+flax_model.msgpack filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

added_tokens.json ADDED Viewed

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

+{
+  "</s>": 77,
+  "<s>": 76
+}

alphabet.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"labels": ["\u0d7c", "\u0d38", "\u0d02", "\u0d0b", "\u0d39", "\u0d27", "\u0d22", "\u0d20", "\u0d1f", "\u0d2a", "\u0d2f", "\u0d40", "\u0d15", " ", "\u0d30", "\u0d0f", "\u0d09", "\u0d43", "\u0d7a", "\u0d23", "\u0d3f", "\u200c", "\u0d7d", "\u0d4a", "\u0d32", "\u0d57", "\u0d18", "\u0d4c", "\u0d26", "\u0d2c", "\u0d1b", "\u0d1d", "\u0d0a", "\u0d28", "\u0d4b", "\u0d71", "\u0d07", "\u0d10", "\u0d48", "\u0d03", "\u0d3e", "\u0d1a", "\u0d47", "\u0d25", "\u0d21", "\u0d0e", "\u0d37", "\u0d06", "\u0d05", "\u0d2e", "\u0d12", "\u0d36", "\u0d16", "\u0d2b", "\u0d41", "\u0d17", "\u0d33", "\u0d13", "\u0d42", "\u0d35", "\u0d1e", "\u0d31", "\u0d2d", "\u0d7b", "\u0d7e", "\u0d08", "\u0d4d", "\u0d46", "\u0d19", "\u0d24", "\u0d1c", "\u200d", "\u0d14", "\u0d34", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json ADDED Viewed

	@@ -0,0 +1,116 @@

+{
+  "_name_or_path": "gvs/wav2vec2-large-xlsr-malayalam",
+  "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": 0.094,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "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": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.045,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.082,
+  "mask_time_selection": "static",
+  "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": 75,
+  "proj_codevector_dim": 256,
+  "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": "4.40.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 76,
+  "xvector_output_dim": 512
+}

flax_model.msgpack ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:18381d01f5140589dfb1d13754725c976fd7172be4e92a52445f2a13baf638f6
+size 1262081874

language_model/5gram.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd9f03149b1b3079706a8443e0fb569379136fcf8824420674d79e3b7f3b1e2b
+size 1300211103

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

File without changes

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b996970a53f14b6f9e0cfdf10edbe5376c1875fc77c5a864446714a55b91ff
+size 1262119080

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": "Wav2Vec2ProcessorWithLM",
+  "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:b5c39014b08099f35aa8eab263323ff24c61f959eddd9d50dc9716ab0df8afee
+size 1262245399

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": {
+    "74": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "77": {
+      "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": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json ADDED Viewed

	@@ -0,0 +1,78 @@

+{
+  "[PAD]": 75,
+  "[UNK]": 74,
+  "|": 13,
+  "ം": 2,
+  "ഃ": 39,
+  "അ": 48,
+  "ആ": 47,
+  "ഇ": 36,
+  "ഈ": 65,
+  "ഉ": 16,
+  "ഊ": 32,
+  "ഋ": 3,
+  "എ": 45,
+  "ഏ": 15,
+  "ഐ": 37,
+  "ഒ": 50,
+  "ഓ": 57,
+  "ഔ": 72,
+  "ക": 12,
+  "ഖ": 52,
+  "ഗ": 55,
+  "ഘ": 26,
+  "ങ": 68,
+  "ച": 41,
+  "ഛ": 30,
+  "ജ": 70,
+  "ഝ": 31,
+  "ഞ": 60,
+  "ട": 8,
+  "ഠ": 7,
+  "ഡ": 44,
+  "ഢ": 6,
+  "ണ": 19,
+  "ത": 69,
+  "ഥ": 43,
+  "ദ": 28,
+  "ധ": 5,
+  "ന": 33,
+  "പ": 9,
+  "ഫ": 53,
+  "ബ": 29,
+  "ഭ": 62,
+  "മ": 49,
+  "യ": 10,
+  "ര": 14,
+  "റ": 61,
+  "ല": 24,
+  "ള": 56,
+  "ഴ": 73,
+  "വ": 59,
+  "ശ": 51,
+  "ഷ": 46,
+  "സ": 1,
+  "ഹ": 4,
+  "ാ": 40,
+  "ി": 20,
+  "ീ": 11,
+  "ു": 54,
+  "ൂ": 58,
+  "ൃ": 17,
+  "െ": 67,
+  "േ": 42,
+  "ൈ": 38,
+  "ൊ": 23,
+  "ോ": 34,
+  "ൌ": 27,
+  "്": 66,
+  "ൗ": 25,
+  "൱": 35,
+  "ൺ": 18,
+  "ൻ": 63,
+  "ർ": 0,
+  "ൽ": 22,
+  "ൾ": 64,
+  "‌": 21,
+  "‍": 71
+}