Hugging Face's logo

jethrowang
/
webcam_loss_CH_1.0_emb-whisper-tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jethrowang commited on
Commit
9818628
•
1 Parent(s): ca91106

End of training

Browse files
Files changed (1) hide show
  1. README.md +25 -25
README.md CHANGED
@@ -8,19 +8,19 @@ tags:
8
  datasets:
9
  - formospeech/hat_asr_aligned
10
  model-index:
11
- - name: Whisper Tiny Hakka Condenser
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- # Whisper Tiny Hakka Condenser
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: 0.2216
23
- - Cer: 13.1863
24
 
25
  ## Model description
26
 
@@ -39,7 +39,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 1e-05
43
  - train_batch_size: 64
44
  - eval_batch_size: 32
45
  - seed: 42
@@ -53,26 +53,26 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Cer |
55
  |:-------------:|:-------:|:----:|:---------------:|:-------:|
56
- | 1.2175 | 0.9980 | 488 | 1.2419 | 50.2601 |
57
- | 0.3915 | 1.9959 | 976 | 0.5156 | 27.2673 |
58
- | 0.1993 | 2.9939 | 1464 | 0.3351 | 18.1346 |
59
- | 0.121 | 3.9918 | 1952 | 0.2783 | 16.5268 |
60
- | 0.0808 | 4.9898 | 2440 | 0.2555 | 15.1964 |
61
- | 0.0538 | 5.9877 | 2928 | 0.2460 | 14.7722 |
62
- | 0.0348 | 6.9857 | 3416 | 0.2305 | 14.2647 |
63
- | 0.0255 | 7.9836 | 3904 | 0.2224 | 13.6105 |
64
- | 0.019 | 8.9816 | 4392 | 0.2232 | 14.8635 |
65
- | 0.0126 | 9.9796 | 4880 | 0.2214 | 13.4857 |
66
- | 0.0079 | 10.9775 | 5368 | 0.2234 | 13.6510 |
67
- | 0.0058 | 11.9755 | 5856 | 0.2211 | 13.5261 |
68
- | 0.0045 | 12.9734 | 6344 | 0.2206 | 13.9920 |
69
- | 0.0034 | 13.9714 | 6832 | 0.2210 | 13.8082 |
70
- | 0.0029 | 14.9693 | 7320 | 0.2235 | 12.1090 |
71
- | 0.0025 | 15.9673 | 7808 | 0.2203 | 12.2974 |
72
- | 0.0022 | 16.9652 | 8296 | 0.2217 | 12.2847 |
73
- | 0.002 | 17.9632 | 8784 | 0.2218 | 13.2291 |
74
- | 0.0018 | 18.9611 | 9272 | 0.2216 | 13.3285 |
75
- | 0.0018 | 19.9591 | 9760 | 0.2216 | 13.1863 |
76
 
77
 
78
  ### Framework versions
 
8
  datasets:
9
  - formospeech/hat_asr_aligned
10
  model-index:
11
+ - name: Whisper Tiny Hakka Simulated Webcam
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
+ # Whisper Tiny Hakka Simulated Webcam
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: 0.1845
23
+ - Cer: 9.7476
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 0.0001
43
  - train_batch_size: 64
44
  - eval_batch_size: 32
45
  - seed: 42
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Cer |
55
  |:-------------:|:-------:|:----:|:---------------:|:-------:|
56
+ | 0.2444 | 0.9980 | 488 | 0.3550 | 25.2919 |
57
+ | 0.1293 | 1.9959 | 976 | 0.3005 | 32.6282 |
58
+ | 0.0835 | 2.9939 | 1464 | 0.2549 | 15.8437 |
59
+ | 0.0429 | 3.9918 | 1952 | 0.2720 | 23.6551 |
60
+ | 0.0279 | 4.9898 | 2440 | 0.2567 | 17.1440 |
61
+ | 0.0177 | 5.9877 | 2928 | 0.2180 | 13.6903 |
62
+ | 0.0103 | 6.9857 | 3416 | 0.2410 | 14.9398 |
63
+ | 0.007 | 7.9836 | 3904 | 0.2333 | 12.8846 |
64
+ | 0.0052 | 8.9816 | 4392 | 0.2008 | 12.4708 |
65
+ | 0.004 | 9.9796 | 4880 | 0.2393 | 12.1957 |
66
+ | 0.0023 | 10.9775 | 5368 | 0.2057 | 12.9829 |
67
+ | 0.0021 | 11.9755 | 5856 | 0.2098 | 12.4096 |
68
+ | 0.0014 | 12.9734 | 6344 | 0.1898 | 14.2208 |
69
+ | 0.001 | 13.9714 | 6832 | 0.2006 | 10.6954 |
70
+ | 0.0012 | 14.9693 | 7320 | 0.1941 | 13.2117 |
71
+ | 0.0005 | 15.9673 | 7808 | 0.1864 | 11.2548 |
72
+ | 0.0005 | 16.9652 | 8296 | 0.1887 | 10.7012 |
73
+ | 0.0001 | 17.9632 | 8784 | 0.1830 | 10.1197 |
74
+ | 0.0001 | 18.9611 | 9272 | 0.1863 | 9.8146 |
75
+ | 0.0001 | 19.9591 | 9760 | 0.1845 | 9.7476 |
76
 
77
 
78
  ### Framework versions