Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_tiny

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
fcb6309
·
verified ·
1 Parent(s): be0a01e

Training finished

Browse files
Files changed (3) hide show
  1. README.md +18 -18
  2. model.safetensors +1 -1
  3. runs/Jan28_08-45-13_8baacbefc598/events.out.tfevents.1738077535.8baacbefc598.18.1 +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: 0.0125
24
- - Wer: 0.1057
25
- - Cer: 0.0420
26
 
27
  ## Model description
28
 
@@ -57,21 +57,21 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0116 | 1.0 | 469 | 0.0084 | 0.0929 | 0.0328 |
61
- | 0.0066 | 2.0 | 938 | 0.0075 | 0.0923 | 0.0344 |
62
- | 0.0058 | 3.0 | 1407 | 0.0074 | 0.0914 | 0.0346 |
63
- | 0.0041 | 4.0 | 1876 | 0.0077 | 0.0883 | 0.0336 |
64
- | 0.0043 | 5.0 | 2345 | 0.0082 | 0.0892 | 0.0330 |
65
- | 0.0028 | 6.0 | 2814 | 0.0089 | 0.0890 | 0.0344 |
66
- | 0.0024 | 7.0 | 3283 | 0.0094 | 0.0887 | 0.0329 |
67
- | 0.0011 | 8.0 | 3752 | 0.0099 | 0.0901 | 0.0341 |
68
- | 0.0015 | 9.0 | 4221 | 0.0104 | 0.0874 | 0.0316 |
69
- | 0.0017 | 10.0 | 4690 | 0.0108 | 0.0887 | 0.0336 |
70
- | 0.0005 | 11.0 | 5159 | 0.0111 | 0.0847 | 0.0307 |
71
- | 0.0003 | 12.0 | 5628 | 0.0113 | 0.0885 | 0.0331 |
72
- | 0.0003 | 13.0 | 6097 | 0.0115 | 0.0896 | 0.0333 |
73
- | 0.0005 | 14.0 | 6566 | 0.0131 | 0.1070 | 0.0423 |
74
- | 0.001 | 15.0 | 7035 | 0.0116 | 0.0900 | 0.0333 |
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: 0.0094
24
+ - Wer: 0.0890
25
+ - Cer: 0.0345
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.007 | 1.0 | 469 | 0.0077 | 0.0912 | 0.0333 |
61
+ | 0.0066 | 2.0 | 938 | 0.0070 | 0.0890 | 0.0329 |
62
+ | 0.0039 | 3.0 | 1407 | 0.0071 | 0.0867 | 0.0320 |
63
+ | 0.0038 | 4.0 | 1876 | 0.0075 | 0.0872 | 0.0332 |
64
+ | 0.0029 | 5.0 | 2345 | 0.0080 | 0.0854 | 0.0314 |
65
+ | 0.0013 | 6.0 | 2814 | 0.0086 | 0.0840 | 0.0317 |
66
+ | 0.002 | 7.0 | 3283 | 0.0089 | 0.0858 | 0.0313 |
67
+ | 0.0008 | 8.0 | 3752 | 0.0094 | 0.0843 | 0.0321 |
68
+ | 0.0012 | 9.0 | 4221 | 0.0099 | 0.0852 | 0.0318 |
69
+ | 0.0008 | 10.0 | 4690 | 0.0103 | 0.0854 | 0.0321 |
70
+ | 0.0009 | 11.0 | 5159 | 0.0107 | 0.0871 | 0.0325 |
71
+ | 0.0006 | 12.0 | 5628 | 0.0109 | 0.0860 | 0.0325 |
72
+ | 0.0007 | 13.0 | 6097 | 0.0111 | 0.1678 | 0.0709 |
73
+ | 0.0006 | 14.0 | 6566 | 0.0125 | 0.1149 | 0.0466 |
74
+ | 0.0004 | 15.0 | 7035 | 0.0113 | 0.1645 | 0.0699 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:175f221d0f953a85ccdf132f03ff80df9179c5c98928d541d36089a8924c60ef
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679c6e50dbb56cd6cc13946d83b02007b77b78c2134faac7d1966a034bafec1d
3
  size 151061672
runs/Jan28_08-45-13_8baacbefc598/events.out.tfevents.1738077535.8baacbefc598.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5841b9203855e39665707c9235c8cb1d059d8fb101b0a4db3a01a9435936b08a
3
+ size 453