Downloads · 30 days
1
3% of all-time downloads
whisper-large-v2-redistribute
NgQuocThai/whisper-large-v2-redistribute
whisper-large-v2-redistribute is a automatic speech recognition model from NgQuocThai. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
34
Public
Parameters
1.5B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 21, 2025
- Updated
- Sep 21, 2025
- SHA
- c7cb06b3
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
whisper-large-v2-redistribute
This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5264
- Cer: 14.6171
- Wer: 26.5231
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 1.0977 | 1.0 | 2174 | 0.4944 | 18.9625 | 33.4968 |
| 0.6342 | 2.0 | 4348 | 0.4951 | 19.3061 | 33.7957 |
| 0.4642 | 3.0 | 6522 | 0.4744 | 16.6247 | 29.5042 |
| 0.3457 | 4.0 | 8696 | 0.4801 | 16.5709 | 29.3509 |
| 0.2597 | 5.0 | 10870 | 0.4961 | 16.3800 | 29.1517 |
| 0.1951 | 6.0 | 13044 | 0.5093 | 15.2751 | 27.4351 |
| 0.1471 | 7.0 | 15218 | 0.5114 | 15.6411 | 27.5730 |
| 0.1126 | 8.0 | 17392 | 0.5264 | 14.6171 | 26.5231 |
| 0.0898 | 9.0 | 19566 | 0.5311 | 14.9876 | 27.1362 |
| 0.073 | 10.0 | 21740 | 0.5515 | 15.1112 | 27.3661 |
| 0.0613 | 11.0 | 23914 | 0.5559 | 14.6463 | 26.6994 |
| 0.0523 | 12.0 | 26088 | 0.5541 | 14.6980 | 26.4771 |
| 0.0455 | 13.0 | 28262 | 0.5691 | 14.8843 | 26.3315 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.21.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Sep 21, 2025
- Updated
- Sep 21, 2025