Downloads · 30 days
9
22% of all-time downloads
whisper-small-Yspeed2
Gummybear05/whisper-small-Yspeed2
whisper-small-Yspeed2 is a automatic speech recognition model from Gummybear05. 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
41
Public
Parameters
242M
15.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 7, 2024
- Updated
- Nov 7, 2024
- SHA
- 07b6bafe
Base models
Datasets
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-small-Yspeed
This model is a fine-tuned version of openai/whisper-small on the aihub old50 adult freq speed pause changed dataset. It achieves the following results on the evaluation set:
- Loss: 0.2665
- Cer: 6.9314
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.2702 | 0.1289 | 100 | 0.2968 | 8.0592 |
| 0.145 | 0.2579 | 200 | 0.2709 | 7.3661 |
| 0.1116 | 0.3868 | 300 | 0.2877 | 7.8242 |
| 0.1197 | 0.5158 | 400 | 0.2675 | 7.1781 |
| 0.0991 | 0.6447 | 500 | 0.2769 | 7.5540 |
| 0.0936 | 0.7737 | 600 | 0.2747 | 7.3543 |
| 0.0992 | 0.9026 | 700 | 0.2670 | 7.0841 |
| 0.0401 | 1.0309 | 800 | 0.2636 | 8.5468 |
| 0.0292 | 1.1599 | 900 | 0.2653 | 6.8080 |
| 0.0392 | 1.2888 | 1000 | 0.2651 | 7.0312 |
| 0.0324 | 1.4178 | 1100 | 0.2712 | 7.0430 |
| 0.0388 | 1.5467 | 1200 | 0.2690 | 7.0254 |
| 0.0313 | 1.6757 | 1300 | 0.2674 | 7.0195 |
| 0.0321 | 1.8046 | 1400 | 0.2647 | 7.0019 |
| 0.0322 | 1.9336 | 1500 | 0.2665 | 6.9314 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hi
- Created
- Nov 7, 2024
- Updated
- Nov 7, 2024