Hugging Face's logo

Pak-Speech-Processing
/
UrduWhisper

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Urdu
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mwz commited on
Commit
be6641e
•
1 Parent(s): 524c525

End of training

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. model.safetensors +1 -1
  3. runs/Jan15_07-10-58_89de281ab612/events.out.tfevents.1705302661.89de281ab612.288.3 +2 -2
README.md CHANGED
@@ -7,7 +7,7 @@ tags:
7
  - hf-asr-leaderboard
8
  - generated_from_trainer
9
  datasets:
10
- - common_voice_15_0
11
  model-index:
12
  - name: ft_model
13
  results: []
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.6428
24
- - Cer: 20.3444
25
 
26
  ## Model description
27
 
@@ -47,17 +47,17 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 500
50
- - training_steps: 2000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Cer |
56
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
- | 0.3575 | 0.09 | 500 | 0.6935 | 21.6276 |
58
- | 0.517 | 0.19 | 1000 | 0.6908 | 18.8399 |
59
- | 0.4816 | 0.28 | 1500 | 0.6628 | 19.9623 |
60
- | 0.5395 | 0.38 | 2000 | 0.6428 | 20.3444 |
61
 
62
 
63
  ### Framework versions
 
7
  - hf-asr-leaderboard
8
  - generated_from_trainer
9
  datasets:
10
+ - common_voice_14_0
11
  model-index:
12
  - name: ft_model
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.6208
24
+ - Cer: 20.8328
25
 
26
  ## Model description
27
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 500
50
+ - training_steps: 4000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Cer |
56
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
+ | 0.5645 | 0.24 | 1000 | 0.7038 | 49.9136 |
58
+ | 0.5042 | 0.48 | 2000 | 0.6748 | 30.8312 |
59
+ | 0.5075 | 0.73 | 3000 | 0.6371 | 20.6798 |
60
+ | 0.437 | 0.97 | 4000 | 0.6208 | 20.8328 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14eb16f3ca600c8b00e2e832804731bfba7da7c088f94abc9818e8c034563b98
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0de8ed87e98fa7cf75c4372a171a6da275c43577ad364e5ccf0b5e4becca50a
3
  size 290403936
runs/Jan15_07-10-58_89de281ab612/events.out.tfevents.1705302661.89de281ab612.288.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3ecda95d85b47ae1d28f84996c7c52d2f4b2ccfc66e1c0f5083a27408a0a4ed
3
- size 31550
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2846f24f6ece7c95b0cfce91e5f134f33ccfca540d8a34b9845db68d5873288f
3
+ size 31904