Hugging Face's logo

Baselhany
/
Whisper_tiny_tring_large_sample_with_early_stop2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
ad5f403
·
verified ·
1 Parent(s): d232105

Training finished

Browse files
Files changed (3) hide show
  1. README.md +13 -19
  2. model.safetensors +1 -1
  3. runs/Feb02_10-39-04_bdefe136c921/events.out.tfevents.1738496800.bdefe136c921.18.1 +3 -0
README.md CHANGED
@@ -20,9 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0074
24
- - Wer: 0.1224
25
- - Cer: 0.0484
26
 
27
  ## Model description
28
 
@@ -55,22 +55,16 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
- |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.007 | 1.0 | 313 | 0.0071 | 0.1361 | 0.0521 |
61
- | 0.0064 | 2.0 | 626 | 0.0070 | 0.1245 | 0.0417 |
62
- | 0.0059 | 3.0 | 939 | 0.0068 | 0.1309 | 0.0478 |
63
- | 0.0052 | 4.0 | 1252 | 0.0070 | 0.1225 | 0.0421 |
64
- | 0.0029 | 5.0 | 1565 | 0.0069 | 0.1225 | 0.0429 |
65
- | 0.0027 | 6.0 | 1878 | 0.0068 | 0.1196 | 0.0401 |
66
- | 0.003 | 7.0 | 2191 | 0.0068 | 0.1144 | 0.0388 |
67
- | 0.0025 | 8.0 | 2504 | 0.0070 | 0.1176 | 0.0385 |
68
- | 0.0022 | 9.0 | 2817 | 0.0071 | 0.1162 | 0.0399 |
69
- | 0.0022 | 10.0 | 3130 | 0.0072 | 0.1184 | 0.0520 |
70
- | 0.0013 | 11.0 | 3443 | 0.0073 | 0.1178 | 0.0379 |
71
- | 0.0022 | 12.0 | 3756 | 0.0074 | 0.1187 | 0.0508 |
72
- | 0.0014 | 13.0 | 4069 | 0.0074 | 0.1214 | 0.0391 |
73
- | 0.0009 | 14.0 | 4382 | 0.0079 | 0.1256 | 0.0482 |
74
 
75
 
76
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0073
24
+ - Wer: 0.1246
25
+ - Cer: 0.0482
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0068 | 0.9801 | 37 | 0.0068 | 0.1158 | 0.0383 |
61
+ | 0.0071 | 1.9801 | 74 | 0.0067 | 0.1171 | 0.0394 |
62
+ | 0.0076 | 2.9801 | 111 | 0.0067 | 0.1222 | 0.0430 |
63
+ | 0.0062 | 3.9801 | 148 | 0.0067 | 0.1258 | 0.0409 |
64
+ | 0.005 | 4.9801 | 185 | 0.0068 | 0.1254 | 0.0406 |
65
+ | 0.0042 | 5.9801 | 222 | 0.0068 | 0.1242 | 0.0417 |
66
+ | 0.0055 | 6.9801 | 259 | 0.0070 | 0.1258 | 0.0425 |
67
+ | 0.0049 | 7.9801 | 296 | 0.0071 | 0.1240 | 0.0394 |
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58b19307b82082cf800a0059e6e51aa405082eb37976ece64b31e2b41c578cf
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f43ba71ef48b7b89beb71d7e0a221ba5b651149e7a03cde66b5d56368ee563e
3
  size 151061672
runs/Feb02_10-39-04_bdefe136c921/events.out.tfevents.1738496800.bdefe136c921.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a1e229fc785ba1fc7256c91808f3214db0f7a88a95482927dca7e17cfd7199
3
+ size 453