Hugging Face's logo

jethrowang
/
webcam_loss_CH_1.0-whisper-tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jethrowang commited on
Commit
b9ab8ff
•
1 Parent(s): 082675e

End of training

Browse files
Files changed (3) hide show
  1. README.md +26 -16
  2. model.safetensors +1 -1
  3. runs/Aug12_12-01-25_nv3090/events.out.tfevents.1723435289.nv3090.159549.0 +2 -2
README.md CHANGED
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the HAT ASR Aligned dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1725
23
- - Cer: 9.9857
24
 
25
  ## Model description
26
 
@@ -45,24 +45,34 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 488
49
- - training_steps: 4880
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Cer |
55
- |:-------------:|:------:|:----:|:---------------:|:-------:|
56
- | 0.1836 | 0.9980 | 488 | 0.3309 | 23.7210 |
57
- | 0.0912 | 1.9959 | 976 | 0.2595 | 24.4238 |
58
- | 0.0437 | 2.9939 | 1464 | 0.2246 | 16.7418 |
59
- | 0.0224 | 3.9918 | 1952 | 0.2424 | 13.6799 |
60
- | 0.0109 | 4.9898 | 2440 | 0.2150 | 13.2395 |
61
- | 0.0046 | 5.9877 | 2928 | 0.2082 | 11.5935 |
62
- | 0.001 | 6.9857 | 3416 | 0.1851 | 12.9748 |
63
- | 0.0009 | 7.9836 | 3904 | 0.1855 | 11.5866 |
64
- | 0.0004 | 8.9816 | 4392 | 0.1733 | 11.0676 |
65
- | 0.0004 | 9.9796 | 4880 | 0.1725 | 9.9857 |
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the HAT ASR Aligned dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.1884
23
+ - Cer: 9.2679
24
 
25
  ## Model description
26
 
 
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 976
49
+ - training_steps: 9760
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
55
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|
56
+ | 0.2208 | 0.9980 | 488 | 0.3739 | 25.8594 |
57
+ | 0.1188 | 1.9959 | 976 | 0.2960 | 24.9116 |
58
+ | 0.0782 | 2.9939 | 1464 | 0.2618 | 18.5519 |
59
+ | 0.041 | 3.9918 | 1952 | 0.2452 | 18.9357 |
60
+ | 0.0251 | 4.9898 | 2440 | 0.2292 | 17.5810 |
61
+ | 0.0169 | 5.9877 | 2928 | 0.2557 | 15.4137 |
62
+ | 0.011 | 6.9857 | 3416 | 0.2254 | 17.0585 |
63
+ | 0.0072 | 7.9836 | 3904 | 0.2343 | 12.5136 |
64
+ | 0.0051 | 8.9816 | 4392 | 0.2362 | 12.3864 |
65
+ | 0.0044 | 9.9796 | 4880 | 0.2261 | 12.0570 |
66
+ | 0.0024 | 10.9775 | 5368 | 0.2191 | 11.3219 |
67
+ | 0.0024 | 11.9755 | 5856 | 0.2158 | 12.1056 |
68
+ | 0.0012 | 12.9734 | 6344 | 0.2027 | 9.9140 |
69
+ | 0.0008 | 13.9714 | 6832 | 0.2002 | 9.7973 |
70
+ | 0.0003 | 14.9693 | 7320 | 0.2084 | 10.1822 |
71
+ | 0.001 | 15.9673 | 7808 | 0.1990 | 9.9082 |
72
+ | 0.0002 | 16.9652 | 8296 | 0.1946 | 9.4355 |
73
+ | 0.0001 | 17.9632 | 8784 | 0.1909 | 9.1361 |
74
+ | 0.0001 | 18.9611 | 9272 | 0.1901 | 9.0517 |
75
+ | 0.0001 | 19.9591 | 9760 | 0.1884 | 9.2679 |
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bce2779fc52089ff8d577a8762f43ae5f788c0d2a6d923d8ee44669de7993b0
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36c57750136151315af724d7a86b2734401e15efb7c28894dfc0d4bdec0143b
3
  size 151061672
runs/Aug12_12-01-25_nv3090/events.out.tfevents.1723435289.nv3090.159549.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad9af9ff2e080c7557220630bb28ff7c2df289b721fef822a218f513e41a20f5
3
- size 54889
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d84aa7f583acbc3ef943df8b94fa119026386461e47ef8573f3f511db1bce9
3
+ size 55243