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
9cf055f
·
verified ·
1 Parent(s): 67853bd

Training finished

Browse files
Files changed (3) hide show
  1. README.md +15 -15
  2. model.safetensors +1 -1
  3. runs/Jan31_17-28-10_325bd650459e/events.out.tfevents.1738368830.325bd650459e.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: 0.0082
24
- - Wer: 0.1370
25
- - Cer: 0.0557
26
 
27
  ## Model description
28
 
@@ -57,18 +57,18 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0094 | 1.0 | 313 | 0.0082 | 0.1922 | 0.0690 |
61
- | 0.0082 | 2.0 | 626 | 0.0082 | 0.1392 | 0.0502 |
62
- | 0.0061 | 3.0 | 939 | 0.0081 | 0.1272 | 0.0432 |
63
- | 0.0051 | 4.0 | 1252 | 0.0080 | 0.1294 | 0.0428 |
64
- | 0.0049 | 5.0 | 1565 | 0.0082 | 0.1238 | 0.0437 |
65
- | 0.0044 | 6.0 | 1878 | 0.0082 | 0.1287 | 0.0446 |
66
- | 0.0036 | 7.0 | 2191 | 0.0084 | 0.1334 | 0.0454 |
67
- | 0.004 | 8.0 | 2504 | 0.0084 | 0.1301 | 0.0432 |
68
- | 0.0024 | 9.0 | 2817 | 0.0086 | 0.1339 | 0.0491 |
69
- | 0.0032 | 10.0 | 3130 | 0.0086 | 0.1260 | 0.0434 |
70
- | 0.0035 | 11.0 | 3443 | 0.0087 | 0.1271 | 0.0439 |
71
- | 0.0027 | 12.0 | 3756 | 0.0089 | 0.1357 | 0.0482 |
72
 
73
 
74
  ### 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: 0.0080
24
+ - Wer: 0.1396
25
+ - Cer: 0.0568
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0054 | 1.0 | 313 | 0.0077 | 0.1316 | 0.0467 |
61
+ | 0.0067 | 2.0 | 626 | 0.0078 | 0.1562 | 0.0649 |
62
+ | 0.0055 | 3.0 | 939 | 0.0077 | 0.1310 | 0.0502 |
63
+ | 0.0042 | 4.0 | 1252 | 0.0078 | 0.1336 | 0.0468 |
64
+ | 0.0036 | 5.0 | 1565 | 0.0078 | 0.1289 | 0.0450 |
65
+ | 0.0043 | 6.0 | 1878 | 0.0079 | 0.1321 | 0.0452 |
66
+ | 0.0036 | 7.0 | 2191 | 0.0079 | 0.1408 | 0.0528 |
67
+ | 0.0026 | 8.0 | 2504 | 0.0080 | 0.1334 | 0.0489 |
68
+ | 0.0024 | 9.0 | 2817 | 0.0081 | 0.1408 | 0.0496 |
69
+ | 0.0026 | 10.0 | 3130 | 0.0083 | 0.1338 | 0.0471 |
70
+ | 0.002 | 11.0 | 3443 | 0.0083 | 0.1374 | 0.0466 |
71
+ | 0.0018 | 12.0 | 3756 | 0.0085 | 0.1338 | 0.0478 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94e747008c4c135e48f52be328f0a93eb48e82758f8e9008afff9dd421218803
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0daf149e2711266b49ce419a1467effd5da6787d363bd20c4b2c822e06d48e9
3
  size 151061672
runs/Jan31_17-28-10_325bd650459e/events.out.tfevents.1738368830.325bd650459e.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22df307c9637b702bdadc2ecf9e6203413e1f231dc02440031e3bc72c8c0c859
3
+ size 453