Hugging Face's logo

whitefox123
/
whisper-large-ar5

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
whitefox123 commited on
Commit
4616f17
•
1 Parent(s): 9bd402f

End of training

Browse files
Files changed (4) hide show
  1. README.md +7 -4
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. runs/Feb19_00-14-40_23fdb26a5aaf/events.out.tfevents.1708301690.23fdb26a5aaf +2 -2
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 128.72072072072072
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the CLARtts dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.1841
39
- - Wer: 128.7207
40
 
41
  ## Model description
42
 
@@ -62,7 +62,7 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 500
65
- - training_steps: 6250
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
@@ -75,6 +75,9 @@ The following hyperparameters were used during training:
75
  | 0.0024 | 6.4 | 4000 | 0.1583 | 136.1802 |
76
  | 0.0012 | 8.0 | 5000 | 0.1708 | 136.3604 |
77
  | 0.0004 | 9.6 | 6000 | 0.1841 | 128.7207 |
 
 
 
78
 
79
 
80
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 156.86486486486487
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
 
36
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the CLARtts dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.1992
39
+ - Wer: 156.8649
40
 
41
  ## Model description
42
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 500
65
+ - training_steps: 9375
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
 
75
  | 0.0024 | 6.4 | 4000 | 0.1583 | 136.1802 |
76
  | 0.0012 | 8.0 | 5000 | 0.1708 | 136.3604 |
77
  | 0.0004 | 9.6 | 6000 | 0.1841 | 128.7207 |
78
+ | 0.0009 | 11.2 | 7000 | 0.1831 | 169.8739 |
79
+ | 0.0003 | 12.8 | 8000 | 0.1885 | 158.7387 |
80
+ | 0.0001 | 14.4 | 9000 | 0.1992 | 156.8649 |
81
 
82
 
83
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb5bcbb53ae781b88fcd551f00c8c360c365ce736feaefe61d5acb7ac222d708
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1121967b20cd2120e2456628c012d647125bd01ad4cada91677e23012217e19
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:669fbc2303bcb9144e31963beea506922ef2050e98159d373423da30cf8e5de5
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a78052d7ca9dd33df68f3c25b240e9c7867341dcf54e4f30bdadf6ffcaf68920
3
  size 1180663192
runs/Feb19_00-14-40_23fdb26a5aaf/events.out.tfevents.1708301690.23fdb26a5aaf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0e9eea637bac3f250ea379136af1145897810f119f7405216109364c64ec513
3
- size 24873
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe205e4d2117c2fb36cda037066cf16c7a3c6181b155b1d99d5da3d9f0daace
3
+ size 27900