Upload lm-boosted W2V2-BERT-Malayalam Model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 76,
+  "<s>": 75
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "\u0d02", "\u0d03", "\u0d05", "\u0d06", "\u0d07", "\u0d08", "\u0d09", "\u0d0a", "\u0d0b", "\u0d0e", "\u0d0f", "\u0d10", "\u0d12", "\u0d13", "\u0d14", "\u0d15", "\u0d16", "\u0d17", "\u0d18", "\u0d19", "\u0d1a", "\u0d1b", "\u0d1c", "\u0d1d", "\u0d1e", "\u0d1f", "\u0d20", "\u0d21", "\u0d22", "\u0d23", "\u0d24", "\u0d25", "\u0d26", "\u0d27", "\u0d28", "\u0d2a", "\u0d2b", "\u0d2c", "\u0d2d", "\u0d2e", "\u0d2f", "\u0d30", "\u0d31", "\u0d32", "\u0d33", "\u0d34", "\u0d35", "\u0d36", "\u0d37", "\u0d38", "\u0d39", "\u0d3e", "\u0d3f", "\u0d40", "\u0d41", "\u0d42", "\u0d43", "\u0d46", "\u0d47", "\u0d48", "\u0d4a", "\u0d4b", "\u0d4c", "\u0d4d", "\u0d57", "\u0d71", "\u0d7a", "\u0d7b", "\u0d7c", "\u0d7d", "\u0d7e", "\u0d7f", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "Bajiyo/w2v-bert-2_7_datasets",
+  "activation_dropout": 0.0,
+  "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": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "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": 74,
+  "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": "4.44.2",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 77,
+  "xvector_output_dim": 512
+}

language_model/3gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8119d59c207845a292a6ff010ac652935dba4b70021f5e6035fa9e0dc04fece
+size 81494251

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab1cd6aa235f41203c790548ab0dc3acb4b688a9a3b342d0bb6fa17b7f28e5d
+size 14807444

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b4ee65c46a5b6609069e35967ec00b07ee37e245b5c91f9e21aae73928fe07
+size 2423130260

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "73": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "76": {
+      "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

@@ -0,0 +1,77 @@
+{
+  "[PAD]": 74,
+  "[UNK]": 73,
+  "|": 0,
+  "ം": 1,
+  "ഃ": 2,
+  "അ": 3,
+  "ആ": 4,
+  "ഇ": 5,
+  "ഈ": 6,
+  "ഉ": 7,
+  "ഊ": 8,
+  "ഋ": 9,
+  "എ": 10,
+  "ഏ": 11,
+  "ഐ": 12,
+  "ഒ": 13,
+  "ഓ": 14,
+  "ഔ": 15,
+  "ക": 16,
+  "ഖ": 17,
+  "ഗ": 18,
+  "ഘ": 19,
+  "ങ": 20,
+  "ച": 21,
+  "ഛ": 22,
+  "ജ": 23,
+  "ഝ": 24,
+  "ഞ": 25,
+  "ട": 26,
+  "ഠ": 27,
+  "ഡ": 28,
+  "ഢ": 29,
+  "ണ": 30,
+  "ത": 31,
+  "ഥ": 32,
+  "ദ": 33,
+  "ധ": 34,
+  "ന": 35,
+  "പ": 36,
+  "ഫ": 37,
+  "ബ": 38,
+  "ഭ": 39,
+  "മ": 40,
+  "യ": 41,
+  "ര": 42,
+  "റ": 43,
+  "ല": 44,
+  "ള": 45,
+  "ഴ": 46,
+  "വ": 47,
+  "ശ": 48,
+  "ഷ": 49,
+  "സ": 50,
+  "ഹ": 51,
+  "ാ": 52,
+  "ി": 53,
+  "ീ": 54,
+  "ു": 55,
+  "ൂ": 56,
+  "ൃ": 57,
+  "െ": 58,
+  "േ": 59,
+  "ൈ": 60,
+  "ൊ": 61,
+  "ോ": 62,
+  "ൌ": 63,
+  "്": 64,
+  "ൗ": 65,
+  "൱": 66,
+  "ൺ": 67,
+  "ൻ": 68,
+  "ർ": 69,
+  "ൽ": 70,
+  "ൾ": 71,
+  "ൿ": 72
+}