Hugging Face's logo

leduytan93
/
Fine-Tune-XLSR-Wav2Vec2-Speech2Text-Vietnamese

Automatic Speech Recognition
Transformers
PyTorch
JAX
Vietnamese
wav2vec2
language-modeling
audio
speech
xlsr-fine-tuning-week
Eval Results
Inference Endpoints
Model card Files Community
1
tanld@jaist.ac.jp commited on
Commit
a512dc1
•
1 Parent(s): 1a6f2d0

update

Browse files
Files changed (6) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +1 -1
  3. scheduler.pt +1 -1
  4. tokenizer_config.json +1 -1
  5. trainer_state.json +15 -15
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-29 12:40:04.541683/checkpoint-75",
3
  "activation_dropout": 0.1,
4
  "apply_spec_augment": true,
5
  "architectures": [
 
1
  {
2
+ "_name_or_path": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-30 03:49:51.885947/checkpoint-188",
3
  "activation_dropout": 0.1,
4
  "apply_spec_augment": true,
5
  "architectures": [
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d96518fe607202354c9263b805edc60c9a3fab50787541859a8ec404b0c0ce23
3
  size 1262372503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52aabb9601897593d223829be973034d7e3642732dacf8d08145b7400b88c517
3
  size 1262372503
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fade7a3b8bb9018ff522b8e7a49e1ee2b795bd4243903aeb0ca28991c0e9c3c
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be3cf714050ec6021a49e7592be7bbe882d5946ab49f060f67a35f53b968024
3
  size 623
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/root/.cache/huggingface/transformers/8892bd2ba1de4982047602e38927ac6f215a3c401e48d5ed39a5341ed475633e.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-29 12:40:04.541683/checkpoint-75"}
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/root/.cache/huggingface/transformers/8892bd2ba1de4982047602e38927ac6f215a3c401e48d5ed39a5341ed475633e.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-30 03:49:51.885947/checkpoint-188"}
trainer_state.json CHANGED
@@ -1,32 +1,32 @@
1
  {
2
- "best_metric": 0.06104659661650658,
3
- "best_model_checkpoint": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-29 13:44:02.238365/checkpoint-25",
4
  "epoch": 2.0,
5
- "global_step": 50,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
- "eval_loss": 0.06104659661650658,
13
- "eval_runtime": 82.3366,
14
- "eval_samples_per_second": 9.23,
15
- "eval_wer": 0.16317016317016317,
16
- "step": 25
17
  },
18
  {
19
  "epoch": 2.0,
20
- "eval_loss": 0.06628068536520004,
21
- "eval_runtime": 83.5033,
22
- "eval_samples_per_second": 9.101,
23
- "eval_wer": 0.16161616161616163,
24
- "step": 50
25
  }
26
  ],
27
- "max_steps": 250,
28
  "num_train_epochs": 10,
29
- "total_flos": 2.075614232631e+17,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
+ "best_metric": 0.06665504723787308,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Speech-To-Text-2021/XLSR-Wav2Vec2/2021-05-30 06:03:07.501105/checkpoint-104",
4
  "epoch": 2.0,
5
+ "global_step": 208,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 1.0,
12
+ "eval_loss": 0.06665504723787308,
13
+ "eval_runtime": 58.9145,
14
+ "eval_samples_per_second": 12.9,
15
+ "eval_wer": 0.16718466718466718,
16
+ "step": 104
17
  },
18
  {
19
  "epoch": 2.0,
20
+ "eval_loss": 0.08242081105709076,
21
+ "eval_runtime": 59.6192,
22
+ "eval_samples_per_second": 12.748,
23
+ "eval_wer": 0.17741517741517743,
24
+ "step": 208
25
  }
26
  ],
27
+ "max_steps": 1040,
28
  "num_train_epochs": 10,
29
+ "total_flos": 3.822833464004777e+17,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f628a2baa271d692db28ee812eab102c39c44f9cf320b0ccd19f16f8ca01a4a3
3
  size 2351
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a0074b0b070a1eff7f2b751d8c57561cef8f4ed4ff04c35a15c091e268d891
3
  size 2351