Hugging Face's logo

Thunpitcha
/
wav2vec2-base-thai-5-google-colab

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Thunpitcha commited on
Commit
b68f0af
•
1 Parent(s): fc64810

End of training

Browse files
Files changed (5) hide show
  1. README.md +25 -18
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/Jan30_06-43-56_a904710133fa/events.out.tfevents.1706597296.a904710133fa.1591.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.6198
21
- - Wer: 0.5833
22
 
23
  ## Model description
24
 
@@ -53,21 +53,28 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|
56
- | 5.8342 | 1.28 | 400 | 3.5303 | 1.0 |
57
- | 3.0206 | 2.56 | 800 | 1.3367 | 0.9586 |
58
- | 1.4665 | 3.84 | 1200 | 0.8291 | 0.8033 |
59
- | 1.1346 | 5.12 | 1600 | 0.7229 | 0.7274 |
60
- | 0.9699 | 6.4 | 2000 | 0.6384 | 0.7101 |
61
- | 0.8754 | 7.68 | 2400 | 0.6393 | 0.6990 |
62
- | 0.8001 | 8.96 | 2800 | 0.6427 | 0.6626 |
63
- | 0.7116 | 10.24 | 3200 | 0.5992 | 0.6534 |
64
- | 0.6743 | 11.52 | 3600 | 0.5936 | 0.6310 |
65
- | 0.632 | 12.8 | 4000 | 0.6278 | 0.6348 |
66
- | 0.5862 | 14.08 | 4400 | 0.6026 | 0.6152 |
67
- | 0.563 | 15.36 | 4800 | 0.6020 | 0.5931 |
68
- | 0.5359 | 16.64 | 5200 | 0.6278 | 0.5954 |
69
- | 0.5065 | 17.92 | 5600 | 0.6273 | 0.5999 |
70
- | 0.4958 | 19.2 | 6000 | 0.6198 | 0.5833 |
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
@@ -75,4 +82,4 @@ The following hyperparameters were used during training:
75
  - Transformers 4.35.2
76
  - Pytorch 2.1.0+cu121
77
  - Datasets 2.16.1
78
- - Tokenizers 0.15.0
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5367
21
+ - Wer: 0.5438
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|
56
+ | 5.8705 | 0.88 | 400 | 3.6557 | 1.0 |
57
+ | 3.2446 | 1.77 | 800 | 1.8761 | 1.0173 |
58
+ | 1.6206 | 2.65 | 1200 | 0.9131 | 0.8479 |
59
+ | 1.2166 | 3.54 | 1600 | 0.7688 | 0.7733 |
60
+ | 1.0517 | 4.42 | 2000 | 0.6680 | 0.7191 |
61
+ | 0.9463 | 5.31 | 2400 | 0.6290 | 0.6903 |
62
+ | 0.8679 | 6.19 | 2800 | 0.5944 | 0.6736 |
63
+ | 0.8053 | 7.08 | 3200 | 0.5609 | 0.6405 |
64
+ | 0.7408 | 7.96 | 3600 | 0.5476 | 0.6294 |
65
+ | 0.6992 | 8.85 | 4000 | 0.5386 | 0.6046 |
66
+ | 0.6593 | 9.73 | 4400 | 0.5338 | 0.5962 |
67
+ | 0.6276 | 10.62 | 4800 | 0.5410 | 0.6087 |
68
+ | 0.5988 | 11.5 | 5200 | 0.5257 | 0.5850 |
69
+ | 0.5625 | 12.39 | 5600 | 0.4970 | 0.5780 |
70
+ | 0.5382 | 13.27 | 6000 | 0.5132 | 0.5638 |
71
+ | 0.5208 | 14.16 | 6400 | 0.5323 | 0.5696 |
72
+ | 0.5041 | 15.04 | 6800 | 0.5287 | 0.5644 |
73
+ | 0.4742 | 15.93 | 7200 | 0.5302 | 0.5744 |
74
+ | 0.4679 | 16.81 | 7600 | 0.5347 | 0.5501 |
75
+ | 0.453 | 17.7 | 8000 | 0.5413 | 0.5498 |
76
+ | 0.4424 | 18.58 | 8400 | 0.5418 | 0.5429 |
77
+ | 0.4283 | 19.47 | 8800 | 0.5367 | 0.5438 |
78
 
79
 
80
  ### Framework versions
 
82
  - Transformers 4.35.2
83
  - Pytorch 2.1.0+cu121
84
  - Datasets 2.16.1
85
+ - Tokenizers 0.15.1
config.json CHANGED
@@ -85,7 +85,7 @@
85
  "num_hidden_layers": 24,
86
  "num_negatives": 100,
87
  "output_hidden_size": 1024,
88
- "pad_token_id": 87,
89
  "proj_codevector_dim": 768,
90
  "tdnn_dilation": [
91
  1,
@@ -111,6 +111,6 @@
111
  "torch_dtype": "float32",
112
  "transformers_version": "4.35.2",
113
  "use_weighted_layer_sum": false,
114
- "vocab_size": 90,
115
  "xvector_output_dim": 512
116
  }
 
85
  "num_hidden_layers": 24,
86
  "num_negatives": 100,
87
  "output_hidden_size": 1024,
88
+ "pad_token_id": 88,
89
  "proj_codevector_dim": 768,
90
  "tdnn_dilation": [
91
  1,
 
111
  "torch_dtype": "float32",
112
  "transformers_version": "4.35.2",
113
  "use_weighted_layer_sum": false,
114
+ "vocab_size": 91,
115
  "xvector_output_dim": 512
116
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b011f2261ea7efb44b9449ab236854713ed633112bf067ecfd5429b0c09d108
3
- size 1262176480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce205b18b27bcf9a0745c460df46612539bab9a4df3476882cc73ff71755754e
3
+ size 1262180580
runs/Jan30_06-43-56_a904710133fa/events.out.tfevents.1706597296.a904710133fa.1591.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7331f781142432c4938f499434ae4c74cc5cd9f5155eaac399bceb9fe642712
3
+ size 16701
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6561b2290f8c8e68955551313cf8b321be7e3d8459ee73e3a8836afd2c89e363
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9358fc125e9b25d16886f81e4ed849ac9742f87a22181400049401ce8c07ba32
3
  size 4600