Update from Mahalakshmi

.gitattributes

@@ -25,3 +25,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gitignore filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
+*.arpa filter=lfs diff=lfs merge=lfs -text
+*.txt filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1 +1,3 @@
-checkpoint-*/
+version https://git-lfs.github.com/spec/v1
+oid sha256:750c10cd267eec2ff1b7afb10688e624b33cf558eef41ed63e00ef640e7fe38a
+size 13

added_tokens.json

@@ -1 +1,3 @@
-{"<s>": 52, "</s>": 53}
+version https://git-lfs.github.com/spec/v1
+oid sha256:43526c6b42b96e56b0bc000b25b394f29fbe53324d4a6b0ec479eed43ae63349
+size 23

alphabet.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2940b80d74250950dc253af7ecae795ea60a6a3c84558daa16e32879ef7bc5
+size 548

config.json

@@ -1,116 +1,3 @@
-{
-  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
-  "activation_dropout": 0.0,
-  "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": 0.0,
-  "feat_quantizer_dropout": 0.0,
-  "final_dropout": 0.0,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
-  "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": 0.05,
-  "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": 51,
-  "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": "4.17.0.dev0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 54,
-  "xvector_output_dim": 512
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ede69bd2d13380480b53a8b3d13370a61081e3572b960f3135465e7e94659a
+size 2314

language_model/5gram_correct.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0c736f3e71c78722b9ba866e8255156f6023b6138f653d03554403796d0886
+size 247315725

language_model/attrs.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ffd02e1ceef6517476e72ebe7997ddef7e92d27cb5a23d6695d64c4317d6ad
+size 78

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39385fac9c06769ac7a6259e5f39c8011bc5ff2f9a7d53f33a3f472ac51436f
+size 3420726

preprocessor_config.json

@@ -1,8 +1,3 @@
-{
-  "do_normalize": true,
-  "feature_size": 1,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": true,
-  "sampling_rate": 16000
-}
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c594304e9d9832162bedd5345051df29e8daf458a845cbed58c6ede23ceeae3
+size 262

special_tokens_map.json

@@ -1 +1,3 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d4108744f9b30c57365da221c760137c262a6ddfa4a71a9a68a561d7b842ee
+size 502

tokenizer_config.json

@@ -1 +1,3 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ffa4d0803a58aab0bb06b3cd4515c627058fb05d13d28e8091277be16de818
+size 349

vocab.json

@@ -1 +1,3 @@
-{"ீ": 0, "'": 1, "ு": 2, "த": 3, "ஞ": 4, "ி": 5, "ய": 6, "உ": 7, "ஒ": 8, "ை": 9, "ோ": 10, "ா": 11, "ஜ": 12, "ம": 13, "ஈ": 14, "ழ": 15, "ஏ": 16, "ல": 17, "ங": 18, "ள": 19, "ொ": 20, "ப": 21, "ஃ": 22, "ஆ": 23, "ூ": 24, "்": 25, "ௌ": 26, "ட": 27, "ஐ": 28, "அ": 29, "’": 30, "ெ": 31, "ற": 32, "ண": 33, "ச": 34, "வ": 35, "ஸ": 36, "ஔ": 37, "ன": 38, "ஷ": 39, "ஓ": 40, "ர": 41, "எ": 42, "ே": 44, "ஊ": 45, "ஹ": 46, "ந": 47, "இ": 48, "க": 49, "|": 43, "[UNK]": 50, "[PAD]": 51}
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d593af25445e3129a95927e45c84f8d4414d9322e4472ffb84bcbd87b965f8
+size 562