Downloads · 30 days
2
8% of all-time downloads
whisper-a-nomi-16
susmitabhatt/whisper-a-nomi-16
whisper-a-nomi-16 is a automatic speech recognition model from susmitabhatt. 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
26
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
- Dec 6, 2024
- Updated
- Dec 6, 2024
- SHA
- 259ccf40
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-a-nomi-16
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0334
- Wer: 10.9026
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: 0.0004
- 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: 132
- num_epochs: 16
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 88 | 0.0818 | 50.4915 |
| 0.9011 | 2.0 | 176 | 0.0692 | 30.5630 |
| 0.1774 | 3.0 | 264 | 0.0428 | 25.5585 |
| 0.0484 | 4.0 | 352 | 0.0953 | 27.9714 |
| 0.0393 | 5.0 | 440 | 0.0466 | 16.0858 |
| 0.0488 | 6.0 | 528 | 0.0490 | 21.5371 |
| 0.024 | 7.0 | 616 | 0.0281 | 18.0518 |
| 0.0076 | 8.0 | 704 | 0.0316 | 9.0259 |
| 0.0076 | 9.0 | 792 | 0.0253 | 13.2261 |
| 0.0023 | 10.0 | 880 | 0.0269 | 10.8132 |
| 0.0011 | 11.0 | 968 | 0.0313 | 10.0089 |
| 0.0002 | 12.0 | 1056 | 0.0364 | 10.0089 |
| 0.0003 | 13.0 | 1144 | 0.0350 | 10.9920 |
| 0.0 | 14.0 | 1232 | 0.0336 | 10.9920 |
| 0.0 | 15.0 | 1320 | 0.0335 | 10.9920 |
| 0.0 | 16.0 | 1408 | 0.0334 | 10.9026 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Dec 6, 2024
- Updated
- Dec 6, 2024