Hugging Face's logo

ashpandian
/
audio_speech_recognition-1b-ATC

Automatic Speech Recognition
Transformers
Safetensors
English
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Community
ashpandian commited on
Commit
26e628b
•
1 Parent(s): c3c2c7f

End of training

Browse files
Files changed (3) hide show
  1. README.md +13 -11
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -1,27 +1,27 @@
1
  ---
2
  language:
3
- - sv
4
  license: apache-2.0
5
- base_model: openai/whisper-small
6
  tags:
7
  - hf-asr-leaderboard
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: WhisperSmallSwedishBirgerMoell
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # WhisperSmallSwedishBirgerMoell
20
 
21
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0167
24
- - Wer: 0.0
25
 
26
  ## Model description
27
 
@@ -46,16 +46,18 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 50
50
- - training_steps: 100
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:------:|:----:|:---------------:|:------:|
57
- | 0.6142 | 0.0422 | 50 | 0.1323 | 5.4545 |
58
- | 0.3295 | 0.0845 | 100 | 0.0167 | 0.0 |
 
 
59
 
60
 
61
  ### Framework versions
 
1
  ---
2
  language:
3
+ - en
4
  license: apache-2.0
5
+ base_model: openai/whisper-large-v3
6
  tags:
7
  - hf-asr-leaderboard
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
+ - name: Whisper-large-v3-atc
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # Whisper-large-v3-atc
20
 
21
+ This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the atc_dataset dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2187
24
+ - Wer: 7.4754
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
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 | Wer |
56
  |:-------------:|:------:|:----:|:---------------:|:------:|
57
+ | 0.19 | 0.8446 | 1000 | 0.2450 | 9.4369 |
58
+ | 0.1105 | 1.6892 | 2000 | 0.2092 | 8.4916 |
59
+ | 0.047 | 2.5338 | 3000 | 0.2069 | 7.9794 |
60
+ | 0.017 | 3.3784 | 4000 | 0.2187 | 7.4754 |
61
 
62
 
63
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:403d778f10527c1675c701505dc4d571e13b02903d2dd0a3e6616d025e20d6ee
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5ac8b8b95c3a0dabdb005a1429cac08223be449bc7e624b3b40087b706fa18d
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:a056f12983daa555e7fea2cf928b81e8884e5c003498a3fc411d5d077df37655
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11342d1228091b70cdafb26a3aa8bf93df497f2c7d4bb00d8fd29660b2190836
3
  size 1180663192