Hugging Face's logo

Baselhany
/
Whisper_tiny_tring_large_sample_with_early_stop2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
7aced9f
·
verified ·
1 Parent(s): c341583

Training finished

Browse files
Files changed (3) hide show
  1. README.md +12 -20
  2. model.safetensors +1 -1
  3. runs/Jan30_19-03-53_31b3690b2c43/events.out.tfevents.1738278444.31b3690b2c43.18.1 +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: 0.0100
24
- - Wer: 0.1520
25
- - Cer: 0.0580
26
 
27
  ## Model description
28
 
@@ -55,23 +55,15 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
- |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
- | 0.0083 | 1.0 | 313 | 0.0106 | 0.1573 | 0.0532 |
61
- | 0.0075 | 2.0 | 626 | 0.0103 | 0.1544 | 0.0535 |
62
- | 0.0076 | 3.0 | 939 | 0.0097 | 0.1605 | 0.0581 |
63
- | 0.0059 | 4.0 | 1252 | 0.0095 | 0.1582 | 0.0562 |
64
- | 0.0056 | 5.0 | 1565 | 0.0094 | 0.1533 | 0.0623 |
65
- | 0.0064 | 6.0 | 1878 | 0.0094 | 0.1736 | 0.0610 |
66
- | 0.0052 | 7.0 | 2191 | 0.0094 | 0.1560 | 0.0560 |
67
- | 0.0046 | 8.0 | 2504 | 0.0093 | 0.1674 | 0.0567 |
68
- | 0.0036 | 9.0 | 2817 | 0.0096 | 0.1437 | 0.0482 |
69
- | 0.0036 | 10.0 | 3130 | 0.0095 | 0.1522 | 0.0518 |
70
- | 0.0032 | 11.0 | 3443 | 0.0095 | 0.1508 | 0.0520 |
71
- | 0.0023 | 12.0 | 3756 | 0.0096 | 0.1466 | 0.0487 |
72
- | 0.0028 | 13.0 | 4069 | 0.0096 | 0.1426 | 0.0461 |
73
- | 0.0028 | 14.0 | 4382 | 0.0100 | 0.1508 | 0.0582 |
74
- | 0.0023 | 14.9536 | 4680 | 0.0097 | 0.1403 | 0.0455 |
75
 
76
 
77
  ### 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: 0.0088
24
+ - Wer: 0.1392
25
+ - Cer: 0.0529
26
 
27
  ## Model description
28
 
 
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0087 | 1.0 | 313 | 0.0090 | 0.1752 | 0.0620 |
61
+ | 0.0069 | 2.0 | 626 | 0.0088 | 0.1385 | 0.0468 |
62
+ | 0.007 | 3.0 | 939 | 0.0087 | 0.1595 | 0.0576 |
63
+ | 0.0052 | 4.0 | 1252 | 0.0088 | 0.1329 | 0.0420 |
64
+ | 0.0055 | 5.0 | 1565 | 0.0086 | 0.1571 | 0.0525 |
65
+ | 0.004 | 6.0 | 1878 | 0.0086 | 0.1609 | 0.0575 |
66
+ | 0.0034 | 7.0 | 2191 | 0.0089 | 0.1372 | 0.0447 |
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc0b2c74e468ae6fcfbdef1358248a204e1999c1457f19cc344ae01027a7d539
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c55fa766b6e535cbcb7548aa2bfe8b5fa409546bf0e12d0b6794a7990939b1
3
  size 151061672
runs/Jan30_19-03-53_31b3690b2c43/events.out.tfevents.1738278444.31b3690b2c43.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c970877a3bc8f9645a0e24e5e1e2f75e0ea37fe44d577eaaa79f7078b271ab96
3
+ size 453