Hugging Face's logo

Cantaosu
/
wavlm_torgo_0H

Automatic Speech Recognition
Transformers
Safetensors
wavlm
Generated from Trainer
Inference Endpoints
Model card Files Community
Cantaosu commited on
Commit
9719649
•
1 Parent(s): 74e7a1a

End of training

Browse files
Files changed (3) hide show
  1. README.md +47 -10
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
- base_model: microsoft/wavlm-base
5
  metrics:
6
  - wer
7
  model-index:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 4.2232
20
  - Wer: 1.0
21
 
22
  ## Model description
@@ -43,18 +43,55 @@ The following hyperparameters were used during training:
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 1000
46
- - num_epochs: 1
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Wer |
52
- |:-------------:|:------:|:----:|:---------------:|:---:|
53
- | 35.3869 | 0.1882 | 500 | 5.7758 | 1.0 |
54
- | 4.2078 | 0.3764 | 1000 | 4.3393 | 1.0 |
55
- | 3.9747 | 0.5645 | 1500 | 4.3099 | 1.0 |
56
- | 3.5744 | 0.7527 | 2000 | 4.1995 | 1.0 |
57
- | 3.6577 | 0.9409 | 2500 | 4.2232 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
1
  ---
2
+ base_model: microsoft/wavlm-base
3
  tags:
4
  - generated_from_trainer
 
5
  metrics:
6
  - wer
7
  model-index:
 
16
 
17
  This model is a fine-tuned version of [microsoft/wavlm-base](https://huggingface.co/microsoft/wavlm-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 4.2230
20
  - Wer: 1.0
21
 
22
  ## Model description
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 1000
46
+ - num_epochs: 8
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:------:|:-----:|:---------------:|:---:|
53
+ | 36.5759 | 0.1882 | 500 | 5.7798 | 1.0 |
54
+ | 4.1355 | 0.3764 | 1000 | 4.3661 | 1.0 |
55
+ | 3.9484 | 0.5645 | 1500 | 4.2577 | 1.0 |
56
+ | 3.6159 | 0.7527 | 2000 | 4.1272 | 1.0 |
57
+ | 3.6944 | 0.9409 | 2500 | 3.9745 | 1.0 |
58
+ | 3.8285 | 1.1291 | 3000 | 4.0134 | 1.0 |
59
+ | 3.6116 | 1.3173 | 3500 | 4.1692 | 1.0 |
60
+ | 3.5828 | 1.5055 | 4000 | 4.0013 | 1.0 |
61
+ | 3.5703 | 1.6936 | 4500 | 4.1055 | 1.0 |
62
+ | 3.5841 | 1.8818 | 5000 | 4.1041 | 1.0 |
63
+ | 3.8079 | 2.0700 | 5500 | 4.1574 | 1.0 |
64
+ | 3.5977 | 2.2582 | 6000 | 4.3217 | 1.0 |
65
+ | 3.5523 | 2.4464 | 6500 | 4.1800 | 1.0 |
66
+ | 3.5661 | 2.6346 | 7000 | 4.2053 | 1.0 |
67
+ | 3.5676 | 2.8227 | 7500 | 4.3885 | 1.0 |
68
+ | 3.794 | 3.0109 | 8000 | 4.2958 | 1.0 |
69
+ | 3.5647 | 3.1991 | 8500 | 4.2959 | 1.0 |
70
+ | 3.5805 | 3.3873 | 9000 | 4.3383 | 1.0 |
71
+ | 3.5475 | 3.5755 | 9500 | 4.1639 | 1.0 |
72
+ | 3.5523 | 3.7636 | 10000 | 4.2241 | 1.0 |
73
+ | 3.5982 | 3.9518 | 10500 | 4.3270 | 1.0 |
74
+ | 3.7088 | 4.1400 | 11000 | 4.2886 | 1.0 |
75
+ | 3.561 | 4.3282 | 11500 | 4.2801 | 1.0 |
76
+ | 3.5367 | 4.5164 | 12000 | 4.6914 | 1.0 |
77
+ | 3.5573 | 4.7046 | 12500 | 4.2071 | 1.0 |
78
+ | 3.5613 | 4.8927 | 13000 | 4.4513 | 1.0 |
79
+ | 3.719 | 5.0809 | 13500 | 4.3972 | 1.0 |
80
+ | 3.5376 | 5.2691 | 14000 | 4.3590 | 1.0 |
81
+ | 3.5313 | 5.4573 | 14500 | 4.3130 | 1.0 |
82
+ | 3.5384 | 5.6455 | 15000 | 4.4599 | 1.0 |
83
+ | 3.5755 | 5.8336 | 15500 | 4.3602 | 1.0 |
84
+ | 3.6912 | 6.0218 | 16000 | 4.2520 | 1.0 |
85
+ | 3.532 | 6.2100 | 16500 | 4.2731 | 1.0 |
86
+ | 3.565 | 6.3982 | 17000 | 4.2608 | 1.0 |
87
+ | 3.5328 | 6.5864 | 17500 | 4.2221 | 1.0 |
88
+ | 3.5361 | 6.7746 | 18000 | 4.2500 | 1.0 |
89
+ | 3.4975 | 6.9627 | 18500 | 4.2042 | 1.0 |
90
+ | 3.6749 | 7.1509 | 19000 | 4.2319 | 1.0 |
91
+ | 3.5316 | 7.3391 | 19500 | 4.2101 | 1.0 |
92
+ | 3.5262 | 7.5273 | 20000 | 4.2657 | 1.0 |
93
+ | 3.6605 | 7.7155 | 20500 | 4.2559 | 1.0 |
94
+ | 3.528 | 7.9037 | 21000 | 4.2230 | 1.0 |
95
 
96
 
97
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91348cc114b4b08fc1e3b823b7de81b6ac0857780e96878d6d6457a2358a69f6
3
  size 377656016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07448d8d8cb4bd01bfaa61442a1df69ea6b69f743344b42d0f46f274f2720f56
3
  size 377656016
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47e0ecba95912850d9cbb05786375ada492c10bb3dadcc11ddf4a5034cb264e0
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c85d41cef8f933a1c8c5b4a28fb95ffc1cd39027858c81bde81b952d7cc44c
3
  size 4920