Hugging Face's logo

vrclc
/
W2V2-BERT-withLM-Malayalam

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Malayalam
wav2vec2-bert
Eval Results
Inference Endpoints
Model card Files Metrics Community
kavyamanohar commited on
Commit
082e1a0
•
1 Parent(s): 17545f2

Add LM decoder for W2V2-BERT

Browse files
Files changed (32) hide show
  1. .gitattributes +1 -0
  2. README.md +84 -0
  3. added_tokens.json +4 -0
  4. alphabet.json +1 -0
  5. config.json +82 -0
  6. language_model/attrs.json +1 -0
  7. language_model/trigram.bin +3 -0
  8. language_model/unigrams.txt +3 -0
  9. model.safetensors +3 -0
  10. preprocessor_config.json +11 -0
  11. runs/Jun06_09-38-59_kudsit-dgxserver/events.out.tfevents.1717647788.kudsit-dgxserver.982178.0 +3 -0
  12. runs/Jun07_09-51-55_kudsit-dgxserver/events.out.tfevents.1717735015.kudsit-dgxserver.2838276.0 +3 -0
  13. runs/Jun10_09-40-25_kudsit-dgxserver/events.out.tfevents.1717993399.kudsit-dgxserver.1550159.0 +3 -0
  14. runs/Jun11_09-27-50_kudsit-dgxserver/events.out.tfevents.1718079163.kudsit-dgxserver.1609792.0 +3 -0
  15. runs/Jun12_09-33-10_kudsit-dgxserver/events.out.tfevents.1718165760.kudsit-dgxserver.1818142.0 +3 -0
  16. runs/Jun12_12-23-15_kudsit-dgxserver/events.out.tfevents.1718176015.kudsit-dgxserver.2425066.0 +3 -0
  17. runs/Jun12_12-52-44_kudsit-dgxserver/events.out.tfevents.1718177765.kudsit-dgxserver.2516392.0 +3 -0
  18. runs/Jun12_15-54-47_kudsit-dgxserver/events.out.tfevents.1718188680.kudsit-dgxserver.2842485.0 +3 -0
  19. runs/May09_09-51-20_kudsit-dgxserver/events.out.tfevents.1715229258.kudsit-dgxserver.2929355.0 +3 -0
  20. runs/May10_09-51-58_kudsit-dgxserver/events.out.tfevents.1715315777.kudsit-dgxserver.2880687.0 +3 -0
  21. runs/May13_09-22-04_kudsit-dgxserver/events.out.tfevents.1715573081.kudsit-dgxserver.3533552.0 +3 -0
  22. runs/May21_10-18-35_kudsit-dgxserver/events.out.tfevents.1716267673.kudsit-dgxserver.3533552.1 +3 -0
  23. runs/May22_10-10-07_kudsit-dgxserver/events.out.tfevents.1716353572.kudsit-dgxserver.3860589.0 +3 -0
  24. runs/May22_10-29-23_kudsit-dgxserver/events.out.tfevents.1716354727.kudsit-dgxserver.3904209.0 +3 -0
  25. runs/May23_09-36-51_kudsit-dgxserver/events.out.tfevents.1716437981.kudsit-dgxserver.1620403.0 +3 -0
  26. runs/May24_09-33-51_kudsit-dgxserver/events.out.tfevents.1716524218.kudsit-dgxserver.2342710.0 +3 -0
  27. runs/May24_09-57-08_kudsit-dgxserver/events.out.tfevents.1716525607.kudsit-dgxserver.2365788.0 +3 -0
  28. runs/May27_09-43-08_kudsit-dgxserver/events.out.tfevents.1716783948.kudsit-dgxserver.1401653.0 +3 -0
  29. special_tokens_map.json +30 -0
  30. tokenizer_config.json +48 -0
  31. training_args.bin +3 -0
  32. vocab.json +79 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: facebook/w2v-bert-2.0
3
+ license: mit
4
+ metrics:
5
+ - wer
6
+ tags:
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: w2v-bert-2.0-nonstudio_and_studioRecords
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # w2v-bert-2.0-nonstudio_and_studioRecords
17
+
18
+ This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1722
21
+ - Wer: 0.1299
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 32
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 500
49
+ - num_epochs: 10
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
+ | 1.1416 | 0.46 | 600 | 0.3393 | 0.4616 |
57
+ | 0.1734 | 0.92 | 1200 | 0.2414 | 0.3493 |
58
+ | 0.1254 | 1.38 | 1800 | 0.2205 | 0.2963 |
59
+ | 0.1097 | 1.84 | 2400 | 0.2157 | 0.3133 |
60
+ | 0.0923 | 2.3 | 3000 | 0.1854 | 0.2473 |
61
+ | 0.0792 | 2.76 | 3600 | 0.1939 | 0.2471 |
62
+ | 0.0696 | 3.22 | 4200 | 0.1720 | 0.2282 |
63
+ | 0.0589 | 3.68 | 4800 | 0.1768 | 0.2013 |
64
+ | 0.0552 | 4.14 | 5400 | 0.1635 | 0.1864 |
65
+ | 0.0437 | 4.6 | 6000 | 0.1501 | 0.1826 |
66
+ | 0.0408 | 5.06 | 6600 | 0.1500 | 0.1645 |
67
+ | 0.0314 | 5.52 | 7200 | 0.1559 | 0.1655 |
68
+ | 0.0317 | 5.98 | 7800 | 0.1448 | 0.1553 |
69
+ | 0.022 | 6.44 | 8400 | 0.1592 | 0.1590 |
70
+ | 0.0218 | 6.9 | 9000 | 0.1431 | 0.1458 |
71
+ | 0.0154 | 7.36 | 9600 | 0.1514 | 0.1366 |
72
+ | 0.0141 | 7.82 | 10200 | 0.1540 | 0.1383 |
73
+ | 0.0113 | 8.28 | 10800 | 0.1558 | 0.1391 |
74
+ | 0.0085 | 8.74 | 11400 | 0.1612 | 0.1356 |
75
+ | 0.0072 | 9.2 | 12000 | 0.1697 | 0.1289 |
76
+ | 0.0046 | 9.66 | 12600 | 0.1722 | 0.1299 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.39.3
82
+ - Pytorch 2.1.1+cu121
83
+ - Datasets 2.16.1
84
+ - Tokenizers 0.15.1
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 78,
3
+ "<s>": 77
4
+ }
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
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", "\u0d7a", "\u0d7b", "\u0d7c", "\u0d7d", "\u0d7e", "\u0d7f", "\u200c", "\u200d", "\u2019", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/w2v-bert-2.0",
3
+ "activation_dropout": 0.0,
4
+ "adapter_act": "relu",
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": true,
8
+ "apply_spec_augment": false,
9
+ "architectures": [
10
+ "Wav2Vec2BertForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 768,
15
+ "codevector_dim": 768,
16
+ "conformer_conv_dropout": 0.1,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "ctc_loss_reduction": "mean",
20
+ "ctc_zero_infinity": false,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.0,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.1,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 1024,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "layer_norm_eps": 1e-05,
33
+ "layerdrop": 0.0,
34
+ "left_max_position_embeddings": 64,
35
+ "mask_feature_length": 10,
36
+ "mask_feature_min_masks": 0,
37
+ "mask_feature_prob": 0.0,
38
+ "mask_time_length": 10,
39
+ "mask_time_min_masks": 2,
40
+ "mask_time_prob": 0.0,
41
+ "max_source_positions": 5000,
42
+ "model_type": "wav2vec2-bert",
43
+ "num_adapter_layers": 1,
44
+ "num_attention_heads": 16,
45
+ "num_codevector_groups": 2,
46
+ "num_codevectors_per_group": 320,
47
+ "num_hidden_layers": 24,
48
+ "num_negatives": 100,
49
+ "output_hidden_size": 1024,
50
+ "pad_token_id": 76,
51
+ "position_embeddings_type": "relative_key",
52
+ "proj_codevector_dim": 768,
53
+ "right_max_position_embeddings": 8,
54
+ "rotary_embedding_base": 10000,
55
+ "tdnn_dilation": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 1,
60
+ 1
61
+ ],
62
+ "tdnn_dim": [
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 512,
67
+ 1500
68
+ ],
69
+ "tdnn_kernel": [
70
+ 5,
71
+ 3,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.39.3",
78
+ "use_intermediate_ffn_before_adapter": false,
79
+ "use_weighted_layer_sum": false,
80
+ "vocab_size": 79,
81
+ "xvector_output_dim": 512
82
+ }
language_model/attrs.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
language_model/trigram.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7424cb716afc8937b8a981fa08edadce4f7846006e5d484852140c85ebdecbd
3
+ size 83212686
language_model/unigrams.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab1cd6aa235f41203c790548ab0dc3acb4b688a9a3b342d0bb6fa17b7f28e5d
3
+ size 14807444
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4d075ddf34767b53db1b375cb48f865a7d8b994c06c388e3727e996cff04c7
3
+ size 2423138460
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000,
10
+ "stride": 2
11
+ }
runs/Jun06_09-38-59_kudsit-dgxserver/events.out.tfevents.1717647788.kudsit-dgxserver.982178.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e16256ff1c6c475413ab868f473a07a5bec5ff62ce0540f2067fd52be5abe5
3
+ size 17395
runs/Jun07_09-51-55_kudsit-dgxserver/events.out.tfevents.1717735015.kudsit-dgxserver.2838276.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3984774b9133ba11801161d0255406918a4c0b94169cbfa9dbbecdd8bf3c5304
3
+ size 17395
runs/Jun10_09-40-25_kudsit-dgxserver/events.out.tfevents.1717993399.kudsit-dgxserver.1550159.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298f7fd247f727b191e8e54d75501c0a6b7067cf7c55f4a065d479a29ce12569
3
+ size 17395
runs/Jun11_09-27-50_kudsit-dgxserver/events.out.tfevents.1718079163.kudsit-dgxserver.1609792.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee95747e79986548f7b2143415ae87ae533757eede2962971f0fd1d38fd5a4ec
3
+ size 17395
runs/Jun12_09-33-10_kudsit-dgxserver/events.out.tfevents.1718165760.kudsit-dgxserver.1818142.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4130cc8d2f1587df3ce5c2bc89424b21624035d75072e5bfa00d0c1e36944c92
3
+ size 8259
runs/Jun12_12-23-15_kudsit-dgxserver/events.out.tfevents.1718176015.kudsit-dgxserver.2425066.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d32c3836773cb7d03daef526802200a6e496cb7130f4e306b517ef4400a9648
3
+ size 5932
runs/Jun12_12-52-44_kudsit-dgxserver/events.out.tfevents.1718177765.kudsit-dgxserver.2516392.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2714ae94e0224595e3d7816dff2c7fb93eec517b81082f1615a32825b131808
3
+ size 9106
runs/Jun12_15-54-47_kudsit-dgxserver/events.out.tfevents.1718188680.kudsit-dgxserver.2842485.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81ab4859dde4410497a87953994aebe10bba8f0747bdfeefd62e98a1ba10789
3
+ size 10164
runs/May09_09-51-20_kudsit-dgxserver/events.out.tfevents.1715229258.kudsit-dgxserver.2929355.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f217a71b9bc29321eeecc71c90a7290f6544ac3dfaa5f3ef393e20c7de83871
3
+ size 17395
runs/May10_09-51-58_kudsit-dgxserver/events.out.tfevents.1715315777.kudsit-dgxserver.2880687.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21c203a64bf27f8fcd2c97ce3fa7100e36975dd182aec3711aac4d458fc515c3
3
+ size 17395
runs/May13_09-22-04_kudsit-dgxserver/events.out.tfevents.1715573081.kudsit-dgxserver.3533552.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ff1751a712427ccaf9e5b9ca4b78e90d7a9573b3a53c08a304846dc8af121d
3
+ size 17395
runs/May21_10-18-35_kudsit-dgxserver/events.out.tfevents.1716267673.kudsit-dgxserver.3533552.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b40dea1554aa0ae11f3a0ec4a20502fa937b8cb3871406b68d9d63cf35a4161
3
+ size 17395
runs/May22_10-10-07_kudsit-dgxserver/events.out.tfevents.1716353572.kudsit-dgxserver.3860589.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cead3706cf80d0143505a353cd497e4cad898021548de017591ff35905d4cbc8
3
+ size 5932
runs/May22_10-29-23_kudsit-dgxserver/events.out.tfevents.1716354727.kudsit-dgxserver.3904209.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46f4d150ff065d470c1e908ebffb10bad13e073e7798eb4a4bd21163646c102
3
+ size 17395
runs/May23_09-36-51_kudsit-dgxserver/events.out.tfevents.1716437981.kudsit-dgxserver.1620403.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60a490d762e7e7bfaed96ea801c72e2e466b38ce27dfdb46c233dde9e726bb2
3
+ size 17395
runs/May24_09-33-51_kudsit-dgxserver/events.out.tfevents.1716524218.kudsit-dgxserver.2342710.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23cecb1fe1f55cca409fdf4451be921e38e448f4f703b51919440635f60705a
3
+ size 5932
runs/May24_09-57-08_kudsit-dgxserver/events.out.tfevents.1716525607.kudsit-dgxserver.2365788.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409f29f53f753673d808c87c0a4c5d918cc8b242a396fca1b73951fce585abd6
3
+ size 17395
runs/May27_09-43-08_kudsit-dgxserver/events.out.tfevents.1716783948.kudsit-dgxserver.1401653.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1827e5e3a65d93cba9b12b1b9658d2fb7b6a2b67df5cbc569e362f6c7c24c8
3
+ size 17395
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "75": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "76": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "77": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "78": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "processor_class": "Wav2Vec2ProcessorWithLM",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0fc1d17fddd4ba9c4e62f69e8c05bc25e390c4b473e430f4e1e845a35a0612
3
+ size 4984
vocab.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 76,
3
+ "[UNK]": 75,
4
+ "|": 0,
5
+ "ം": 1,
6
+ "ഃ": 2,
7
+ "അ": 3,
8
+ "ആ": 4,
9
+ "ഇ": 5,
10
+ "ഈ": 6,
11
+ "ഉ": 7,
12
+ "ഊ": 8,
13
+ "ഋ": 9,
14
+ "എ": 10,
15
+ "ഏ": 11,
16
+ "ഐ": 12,
17
+ "ഒ": 13,
18
+ "ഓ": 14,
19
+ "ഔ": 15,
20
+ "ക": 16,
21
+ "ഖ": 17,
22
+ "ഗ": 18,
23
+ "ഘ": 19,
24
+ "ങ": 20,
25
+ "ച": 21,
26
+ "ഛ": 22,
27
+ "ജ": 23,
28
+ "ഝ": 24,
29
+ "ഞ": 25,
30
+ "ട": 26,
31
+ "ഠ": 27,
32
+ "ഡ": 28,
33
+ "ഢ": 29,
34
+ "ണ": 30,
35
+ "ത": 31,
36
+ "ഥ": 32,
37
+ "ദ": 33,
38
+ "ധ": 34,
39
+ "ന": 35,
40
+ "പ": 36,
41
+ "ഫ": 37,
42
+ "ബ": 38,
43
+ "ഭ": 39,
44
+ "മ": 40,
45
+ "യ": 41,
46
+ "ര": 42,
47
+ "റ": 43,
48
+ "ല": 44,
49
+ "ള": 45,
50
+ "ഴ": 46,
51
+ "വ": 47,
52
+ "ശ": 48,
53
+ "ഷ": 49,
54
+ "സ": 50,
55
+ "ഹ": 51,
56
+ "ാ": 52,
57
+ "ി": 53,
58
+ "ീ": 54,
59
+ "ു": 55,
60
+ "ൂ": 56,
61
+ "ൃ": 57,
62
+ "െ": 58,
63
+ "േ": 59,
64
+ "ൈ": 60,
65
+ "ൊ": 61,
66
+ "ോ": 62,
67
+ "ൌ": 63,
68
+ "്": 64,
69
+ "ൗ": 65,
70
+ "ൺ": 66,
71
+ "ൻ": 67,
72
+ "ർ": 68,
73
+ "ൽ": 69,
74
+ "ൾ": 70,
75
+ "ൿ": 71,
76
+ "‌": 72,
77
+ "‍": 73,
78
+ "’": 74
79
+ }