Hugging Face's logo

Baselhany
/
Graduation_Project_Whisper_base_segment

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
Baselhany commited on
Commit
80cea65
·
verified ·
1 Parent(s): 11bccc2

Segementation

Browse files
Files changed (5) hide show
  1. README.md +27 -27
  2. generation_config.json +1 -10
  3. model.safetensors +1 -1
  4. runs/Apr29_01-54-22_29ee97617b26/events.out.tfevents.1745891665.29ee97617b26.19.0 +2 -2
  5. runs/Apr29_01-54-22_29ee97617b26/events.out.tfevents.1745934634.29ee97617b26.19.1 +3 -0
README.md CHANGED
@@ -21,8 +21,8 @@ should probably proofread and complete it, then remove this comment. -->
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.0037
24
- - Wer: 0.0571
25
- - Cer: 0.0223
26
 
27
  ## Model description
28
 
@@ -57,31 +57,31 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
- | 0.0078 | 1.0 | 282 | 0.0037 | 0.0529 | 0.0209 |
61
- | 0.0047 | 2.0 | 564 | 0.0040 | 0.0550 | 0.0208 |
62
- | 0.0018 | 3.0 | 846 | 0.0050 | 0.0646 | 0.0261 |
63
- | 0.0013 | 4.0 | 1128 | 0.0053 | 0.0594 | 0.0224 |
64
- | 0.0009 | 5.0 | 1410 | 0.0062 | 0.0659 | 0.0241 |
65
- | 0.0008 | 6.0 | 1692 | 0.0066 | 0.0659 | 0.0257 |
66
- | 0.0008 | 7.0 | 1974 | 0.0068 | 0.0626 | 0.0243 |
67
- | 0.0006 | 8.0 | 2256 | 0.0072 | 0.0615 | 0.0223 |
68
- | 0.0006 | 9.0 | 2538 | 0.0075 | 0.0668 | 0.0256 |
69
- | 0.0003 | 10.0 | 2820 | 0.0077 | 0.0643 | 0.0238 |
70
- | 0.0003 | 11.0 | 3102 | 0.0082 | 0.0577 | 0.0211 |
71
- | 0.0002 | 12.0 | 3384 | 0.0090 | 0.0643 | 0.0237 |
72
- | 0.0002 | 13.0 | 3666 | 0.0100 | 0.0637 | 0.0222 |
73
- | 0.0001 | 14.0 | 3948 | 0.0100 | 0.0615 | 0.0229 |
74
- | 0.0001 | 15.0 | 4230 | 0.0104 | 0.0603 | 0.0232 |
75
- | 0.0001 | 16.0 | 4512 | 0.0111 | 0.0606 | 0.0216 |
76
- | 0.0001 | 17.0 | 4794 | 0.0115 | 0.0614 | 0.0211 |
77
- | 0.0 | 18.0 | 5076 | 0.0115 | 0.0570 | 0.0196 |
78
- | 0.0 | 19.0 | 5358 | 0.0121 | 0.0614 | 0.0225 |
79
- | 0.0 | 20.0 | 5640 | 0.0119 | 0.0595 | 0.0219 |
80
- | 0.0 | 21.0 | 5922 | 0.0121 | 0.0588 | 0.0209 |
81
- | 0.0 | 22.0 | 6204 | 0.0121 | 0.0597 | 0.0215 |
82
- | 0.0 | 23.0 | 6486 | 0.0121 | 0.0601 | 0.0215 |
83
- | 0.0 | 24.0 | 6768 | 0.0126 | 0.0609 | 0.0234 |
84
- | 0.0 | 24.9130 | 7025 | 0.0121 | 0.0588 | 0.0204 |
85
 
86
 
87
  ### Framework versions
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the quran-ayat-speech-to-text dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 0.0037
24
+ - Wer: 0.0528
25
+ - Cer: 0.0213
26
 
27
  ## Model description
28
 
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0061 | 1.0 | 282 | 0.0036 | 0.0474 | 0.0188 |
61
+ | 0.0039 | 2.0 | 564 | 0.0040 | 0.0552 | 0.0217 |
62
+ | 0.0021 | 3.0 | 846 | 0.0047 | 0.0563 | 0.0222 |
63
+ | 0.0011 | 4.0 | 1128 | 0.0055 | 0.0579 | 0.0200 |
64
+ | 0.0008 | 5.0 | 1410 | 0.0058 | 0.0579 | 0.0225 |
65
+ | 0.0007 | 6.0 | 1692 | 0.0061 | 0.0572 | 0.0194 |
66
+ | 0.0006 | 7.0 | 1974 | 0.0063 | 0.0576 | 0.0208 |
67
+ | 0.0005 | 8.0 | 2256 | 0.0063 | 0.0664 | 0.0246 |
68
+ | 0.0003 | 9.0 | 2538 | 0.0077 | 0.0715 | 0.0254 |
69
+ | 0.0003 | 10.0 | 2820 | 0.0074 | 0.0666 | 0.0256 |
70
+ | 0.0004 | 11.0 | 3102 | 0.0075 | 0.0626 | 0.0244 |
71
+ | 0.0001 | 12.0 | 3384 | 0.0083 | 0.0617 | 0.0234 |
72
+ | 0.0002 | 13.0 | 3666 | 0.0083 | 0.0655 | 0.0228 |
73
+ | 0.0001 | 14.0 | 3948 | 0.0100 | 0.0617 | 0.0219 |
74
+ | 0.0001 | 15.0 | 4230 | 0.0109 | 0.0648 | 0.0224 |
75
+ | 0.0001 | 16.0 | 4512 | 0.0113 | 0.0610 | 0.0196 |
76
+ | 0.0 | 17.0 | 4794 | 0.0120 | 0.0612 | 0.0212 |
77
+ | 0.0001 | 18.0 | 5076 | 0.0127 | 0.0601 | 0.0220 |
78
+ | 0.0 | 19.0 | 5358 | 0.0134 | 0.0581 | 0.0208 |
79
+ | 0.0 | 20.0 | 5640 | 0.0135 | 0.0597 | 0.0226 |
80
+ | 0.0 | 21.0 | 5922 | 0.0134 | 0.0570 | 0.0205 |
81
+ | 0.0 | 22.0 | 6204 | 0.0133 | 0.0579 | 0.0209 |
82
+ | 0.0 | 23.0 | 6486 | 0.0133 | 0.0577 | 0.0208 |
83
+ | 0.0 | 24.0 | 6768 | 0.0138 | 0.0605 | 0.0236 |
84
+ | 0.0 | 24.9130 | 7025 | 0.0134 | 0.0583 | 0.0205 |
85
 
86
 
87
  ### Framework versions
generation_config.json CHANGED
@@ -40,16 +40,7 @@
40
  "bos_token_id": 50257,
41
  "decoder_start_token_id": 50258,
42
  "eos_token_id": 50257,
43
- "input_ids": [
44
- [
45
- 1,
46
- null
47
- ],
48
- [
49
- 2,
50
- 50359
51
- ]
52
- ],
53
  "is_multilingual": true,
54
  "lang_to_id": {
55
  "<|af|>": 50327,
 
40
  "bos_token_id": 50257,
41
  "decoder_start_token_id": 50258,
42
  "eos_token_id": 50257,
43
+ "input_ids": null,
 
 
 
 
 
 
 
 
 
44
  "is_multilingual": true,
45
  "lang_to_id": {
46
  "<|af|>": 50327,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d43ec75e69bc1a82322c0070c5aa7d3f08d0413756672c1feb67e26a38a294
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63622e85d99ce8ba4d1eccbfdbbbcae8338b8348add2f44f59607ec97263af25
3
  size 290403936
runs/Apr29_01-54-22_29ee97617b26/events.out.tfevents.1745891665.29ee97617b26.19.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5d6bc411c5a36fef05ebabd4502839b3d9a982bfb1d3c2f6ebb2606aef1de24
3
- size 74293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639881db507ef1d779b47a97e911944cd57afd51fdf9379bc3a76e8e899eaf82
3
+ size 74647
runs/Apr29_01-54-22_29ee97617b26/events.out.tfevents.1745934634.29ee97617b26.19.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3f227370d19be8a54eb5b1e5bb1fd78b26e3f7f757ec4076dc8812813966f3
3
+ size 453