Hugging Face's logo

Baselhany
/
fine_tune_Whisper_tiny2

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Baselhany commited on
Commit
7933ab1
·
verified ·
1 Parent(s): 4a9453a

Training finished

Browse files
Files changed (3) hide show
  1. README.md +12 -8
  2. model.safetensors +1 -1
  3. runs/Jan17_16-18-37_df96f55df6d0/events.out.tfevents.1737137200.df96f55df6d0.18.1 +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: 0.0109
24
- - Wer: 0.1246
25
- - Cer: 0.0445
26
 
27
  ## Model description
28
 
@@ -41,7 +41,7 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 5e-05
45
  - train_batch_size: 16
46
  - eval_batch_size: 16
47
  - seed: 42
@@ -57,10 +57,14 @@ The following hyperparameters were used during training:
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
- | 0.0147 | 1.0 | 157 | 0.0106 | 0.1202 | 0.0426 |
61
- | 0.0079 | 2.0 | 314 | 0.0113 | 0.1280 | 0.0437 |
62
- | 0.0058 | 3.0 | 471 | 0.0132 | 0.1377 | 0.0494 |
63
- | 0.0041 | 4.0 | 628 | 0.0144 | 0.1430 | 0.0462 |
 
 
 
 
64
 
65
 
66
  ### 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: 0.0101
24
+ - Wer: 0.1150
25
+ - Cer: 0.0408
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 1e-05
45
  - train_batch_size: 16
46
  - eval_batch_size: 16
47
  - seed: 42
 
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
60
+ | 0.0101 | 1.0 | 157 | 0.0101 | 0.1162 | 0.0413 |
61
+ | 0.008 | 2.0 | 314 | 0.0099 | 0.1148 | 0.0406 |
62
+ | 0.0055 | 3.0 | 471 | 0.0100 | 0.1140 | 0.0384 |
63
+ | 0.0079 | 4.0 | 628 | 0.0103 | 0.1155 | 0.0401 |
64
+ | 0.0033 | 5.0 | 785 | 0.0117 | 0.1146 | 0.0409 |
65
+ | 0.0023 | 6.0 | 942 | 0.0121 | 0.1184 | 0.0402 |
66
+ | 0.0011 | 7.0 | 1099 | 0.0133 | 0.1204 | 0.0425 |
67
+ | 0.001 | 8.0 | 1256 | 0.0138 | 0.1166 | 0.0402 |
68
 
69
 
70
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e55f5ad571e350a4f294b1de427bccd2c9a06bf26aa036911c6867e048e7fc9
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5547a16c0c37b445bdf109da08be79822eaae7cd7a14a24414c3fe7cf764459
3
  size 151061672
runs/Jan17_16-18-37_df96f55df6d0/events.out.tfevents.1737137200.df96f55df6d0.18.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5cfd47a2b7027cd9f768247e9a9833dfed73c98e8b8cf5693d0ca3b2d4c389
3
+ size 453