Hugging Face's logo

nrshoudi
/
arabic_speech_ASR_Whisper

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
nrshoudi commited on
Commit
5cca4e4
•
1 Parent(s): 5ba0992

End of training

Browse files
Files changed (4) hide show
  1. README.md +15 -13
  2. adapter_model.safetensors +1 -1
  3. runs/Mar07_13-09-54_8539dde49e16/events.out.tfevents.1709817000.8539dde49e16.2736.1 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_13_0 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6463
22
 
23
  ## Model description
24
 
@@ -38,27 +38,29 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.001
41
- - train_batch_size: 8
42
- - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
46
  - num_epochs: 10
 
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 0.7591 | 1.0 | 300 | 0.7290 |
53
- | 0.5736 | 2.0 | 600 | 0.6492 |
54
- | 0.4507 | 3.0 | 900 | 0.6266 |
55
- | 0.3456 | 4.0 | 1200 | 0.6130 |
56
- | 0.2947 | 5.0 | 1500 | 0.6018 |
57
- | 0.2153 | 6.0 | 1800 | 0.6061 |
58
- | 0.1761 | 7.0 | 2100 | 0.6146 |
59
- | 0.1185 | 8.0 | 2400 | 0.6290 |
60
- | 0.0808 | 9.0 | 2700 | 0.6381 |
61
- | 0.0643 | 10.0 | 3000 | 0.6463 |
62
 
63
 
64
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_13_0 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8332
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.001
41
+ - train_batch_size: 6
42
+ - eval_batch_size: 6
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 50
47
  - num_epochs: 10
48
+ - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 0.9454 | 1.0 | 400 | 0.9238 |
55
+ | 0.846 | 2.0 | 800 | 0.8786 |
56
+ | 0.7349 | 3.0 | 1200 | 0.8355 |
57
+ | 0.6079 | 4.0 | 1600 | 0.8174 |
58
+ | 0.5083 | 5.0 | 2000 | 0.8075 |
59
+ | 0.4655 | 6.0 | 2400 | 0.8072 |
60
+ | 0.3587 | 7.0 | 2800 | 0.8087 |
61
+ | 0.3336 | 8.0 | 3200 | 0.8147 |
62
+ | 0.26 | 9.0 | 3600 | 0.8242 |
63
+ | 0.2193 | 10.0 | 4000 | 0.8332 |
64
 
65
 
66
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc9b07500ad9b1b995296b24e222082e2052703511974288657270f3ca237564
3
  size 2366008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb016e4304b0fd37858aa84010971d2e95d3ad8ed78553f0269934aece406e9
3
  size 2366008
runs/Mar07_13-09-54_8539dde49e16/events.out.tfevents.1709817000.8539dde49e16.2736.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469aeff1bbeb8d8ce2ff34dd9edace7a6c51a5734a3555c6d081095fb4778a52
3
+ size 42699
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2812de18f998158be42208b9a11aa9ae19e4e2d150fd05ca0c5ee076a094bd8
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7901ea0af11ed1bba592a51450e6177b2ee0b46812cb924d0dbea984ffcfaf1
3
  size 5112