Hugging Face's logo

nrshoudi
/
speech_ocean_hubert_mdd

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nrshoudi commited on
Commit
cc245c2
•
1 Parent(s): 82a736e

End of training

Browse files
Files changed (5) hide show
  1. README.md +24 -24
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Apr28_14-59-34_6a55d4679ae0/events.out.tfevents.1714316406.6a55d4679ae0.2079.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: facebook/hubert-large-ll60k
6
  metrics:
7
  - wer
8
  model-index:
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1563
21
- - Wer: 0.0612
22
- - Cer: 0.0573
23
 
24
  ## Model description
25
 
@@ -54,26 +54,26 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
57
- | 24.692 | 0.9873 | 39 | 19.7376 | 0.9997 | 0.9999 |
58
- | 6.7786 | 2.0 | 79 | 3.8382 | 1.0 | 1.0 |
59
- | 3.77 | 2.9873 | 118 | 3.2211 | 1.0 | 1.0 |
60
- | 3.1537 | 4.0 | 158 | 3.1178 | 1.0 | 1.0 |
61
- | 3.0849 | 4.9873 | 197 | 3.0815 | 1.0 | 1.0 |
62
- | 3.08 | 6.0 | 237 | 3.0583 | 1.0 | 1.0 |
63
- | 3.0887 | 6.9873 | 276 | 3.0658 | 1.0 | 1.0 |
64
- | 3.0528 | 8.0 | 316 | 3.0221 | 1.0 | 1.0 |
65
- | 2.9694 | 8.9873 | 355 | 2.8183 | 1.0 | 1.0 |
66
- | 2.6127 | 10.0 | 395 | 2.3266 | 0.9892 | 0.9935 |
67
- | 2.0376 | 10.9873 | 434 | 1.6122 | 0.6557 | 0.6453 |
68
- | 1.692 | 12.0 | 474 | 1.1974 | 0.4865 | 0.4708 |
69
- | 1.245 | 12.9873 | 513 | 0.7927 | 0.2645 | 0.2425 |
70
- | 0.9455 | 14.0 | 553 | 0.5426 | 0.1636 | 0.1371 |
71
- | 0.7612 | 14.9873 | 592 | 0.3803 | 0.1214 | 0.1069 |
72
- | 0.6122 | 16.0 | 632 | 0.2850 | 0.0912 | 0.0824 |
73
- | 0.4748 | 16.9873 | 671 | 0.2247 | 0.0777 | 0.0705 |
74
- | 0.4095 | 18.0 | 711 | 0.1796 | 0.0676 | 0.0626 |
75
- | 0.348 | 18.9873 | 750 | 0.1623 | 0.0638 | 0.0595 |
76
- | 0.3615 | 19.7468 | 780 | 0.1563 | 0.0612 | 0.0573 |
77
 
78
 
79
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/hubert-large-ll60k
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
7
  - wer
8
  model-index:
 
17
 
18
  This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2060
21
+ - Wer: 0.0531
22
+ - Cer: 0.0507
23
 
24
  ## Model description
25
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
57
+ | 42.5933 | 0.9873 | 39 | 36.3096 | 0.9995 | 0.9985 |
58
+ | 15.8463 | 2.0 | 79 | 7.9376 | 1.0 | 1.0 |
59
+ | 6.5393 | 2.9873 | 118 | 4.5528 | 1.0 | 1.0 |
60
+ | 3.9947 | 4.0 | 158 | 3.8592 | 1.0 | 1.0 |
61
+ | 3.8025 | 4.9873 | 197 | 3.8002 | 1.0 | 1.0 |
62
+ | 3.7706 | 6.0 | 237 | 3.7435 | 1.0 | 1.0 |
63
+ | 3.7676 | 6.9873 | 276 | 3.7276 | 1.0 | 1.0 |
64
+ | 3.7353 | 8.0 | 316 | 3.7150 | 1.0 | 1.0 |
65
+ | 3.7126 | 8.9873 | 355 | 3.6717 | 1.0 | 1.0 |
66
+ | 3.5628 | 10.0 | 395 | 3.3098 | 1.0 | 1.0 |
67
+ | 2.837 | 10.9873 | 434 | 2.3304 | 0.8277 | 0.8915 |
68
+ | 2.1018 | 12.0 | 474 | 1.5575 | 0.5441 | 0.6213 |
69
+ | 1.6164 | 12.9873 | 513 | 1.0106 | 0.2678 | 0.2596 |
70
+ | 1.1823 | 14.0 | 553 | 0.6938 | 0.1788 | 0.1509 |
71
+ | 0.9451 | 14.9873 | 592 | 0.4673 | 0.1154 | 0.0925 |
72
+ | 0.7055 | 16.0 | 632 | 0.3455 | 0.0893 | 0.0767 |
73
+ | 0.5434 | 16.9873 | 671 | 0.2803 | 0.0718 | 0.0637 |
74
+ | 0.4867 | 18.0 | 711 | 0.2362 | 0.0608 | 0.0566 |
75
+ | 0.4172 | 18.9873 | 750 | 0.2125 | 0.0551 | 0.0522 |
76
+ | 0.4406 | 19.7468 | 780 | 0.2060 | 0.0531 | 0.0507 |
77
 
78
 
79
  ### Framework versions
config.json CHANGED
@@ -74,10 +74,10 @@
74
  "num_conv_pos_embeddings": 128,
75
  "num_feat_extract_layers": 7,
76
  "num_hidden_layers": 24,
77
- "pad_token_id": 35,
78
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
79
  "torch_dtype": "float32",
80
  "transformers_version": "4.40.0",
81
  "use_weighted_layer_sum": false,
82
- "vocab_size": 38
83
  }
 
74
  "num_conv_pos_embeddings": 128,
75
  "num_feat_extract_layers": 7,
76
  "num_hidden_layers": 24,
77
+ "pad_token_id": 117,
78
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
79
  "torch_dtype": "float32",
80
  "transformers_version": "4.40.0",
81
  "use_weighted_layer_sum": false,
82
+ "vocab_size": 120
83
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:839f30502a5c1b3cc0dd20b4e9c64c15224930e1c2beb80ce1d0a1db84fb7422
3
- size 1261962448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb30c3f021d1cb6a45ee8307c35ac0e61b132ddce915d2a59b49013087a2093
3
+ size 1262298648
runs/Apr28_14-59-34_6a55d4679ae0/events.out.tfevents.1714316406.6a55d4679ae0.2079.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646648a658b28352c0688b1f170b9d6f04384adf6e9c38b0bdfdc320aeddf310
3
+ size 29870
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bd2eccadf8560cf31c4f8cf8879edcc13bcfe49912f9d17980ecf6f1b3af115
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc67eafe12d61e2b2a4f6d97a51e302eec7818741011830e7458182dc240bc8
3
  size 5048