Downloads · 30 days
8
6% of all-time downloads
Whisper-squeezeformer-v9_train_CM
jun-han/Whisper-squeezeformer-v9_train_CM
Whisper-squeezeformer-v9_train_CM is a automatic speech recognition model from jun-han. 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
135
Public
Parameters
269M
36.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Apr 8, 2025
- Updated
- Jun 1, 2025
- SHA
- 979bfae0
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-squeezeformer-v9_train_CM
This model is a fine-tuned version of openai/whisper-small on the common voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.4028
- Wer: 16.4239
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: 20
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2500
- training_steps: 60000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.0739 | 0.7699 | 2500 | 4.0357 | 118.3015 |
| 2.4575 | 1.5399 | 5000 | 0.6239 | 29.9161 |
| 0.4494 | 2.3098 | 7500 | 0.5402 | 20.0608 |
| 0.33 | 3.0798 | 10000 | 0.5597 | 20.0198 |
| 0.4513 | 3.8485 | 12500 | 0.5001 | 20.8211 |
| 0.3154 | 4.6182 | 15000 | 0.4908 | 20.5695 |
| 0.3723 | 7.0056 | 17500 | 0.4729 | 19.6478 |
| 0.2324 | 8.0064 | 20000 | 0.4822 | 19.8000 |
| 0.3342 | 9.0072 | 22500 | 0.4642 | 18.9459 |
| 0.2465 | 10.0080 | 25000 | 0.4679 | 19.1679 |
| 0.3713 | 11.0088 | 27500 | 0.4491 | 18.3519 |
| 0.3587 | 12.0096 | 30000 | 0.4433 | 18.4217 |
| 0.3394 | 13.0104 | 32500 | 0.4363 | 18.0263 |
| 0.3282 | 14.0056 | 35000 | 0.4268 | 17.6648 |
| 0.3305 | 15.0120 | 37500 | 0.4243 | 18.0179 |
| 0.3267 | 16.0064 | 40000 | 0.4233 | 17.3879 |
| 0.3099 | 17.0204 | 42500 | 0.4193 | 17.0835 |
| 0.3094 | 18.0072 | 45000 | 0.4138 | 17.0053 |
| 0.2909 | 19.0076 | 47500 | 0.4146 | 16.9630 |
| 0.299 | 20.0080 | 50000 | 0.4091 | 16.9334 |
| 0.326 | 21.0084 | 52500 | 0.4085 | 16.6522 |
| 0.3333 | 22.0088 | 55000 | 0.4014 | 16.7558 |
| 0.3368 | 23.0092 | 57500 | 0.4018 | 16.3753 |
| 0.3125 | 24.0096 | 60000 | 0.4028 | 16.4239 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0
- Datasets 3.2.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Apr 8, 2025
- Updated
- Jun 1, 2025