Downloads · 30 days
5
25% of all-time downloads
whisper-finetuned-bial
bhattasp/whisper-finetuned-bial
whisper-finetuned-bial is a automatic speech recognition model from bhattasp. 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
20
Public
Parameters
37.8M
1.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Oct 15, 2024
- Updated
- Oct 25, 2024
- SHA
- a011960b
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. -->
bhattasp/whisper-finetuned-bial
This model is a fine-tuned version of openai/whisper-tiny on the Bial dataset. It achieves the following results on the evaluation set:
- Loss: 0.4114
- Wer: 22.7624
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.7741 | 1.0 | 257 | 1.7110 | 41.2738 |
| 0.8015 | 2.0 | 514 | 0.6401 | 38.2903 |
| 0.3439 | 3.0 | 771 | 0.4480 | 28.6366 |
| 0.2409 | 4.0 | 1028 | 0.4146 | 30.2520 |
| 0.1659 | 5.0 | 1285 | 0.4114 | 22.7624 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Oct 15, 2024
- Updated
- Oct 25, 2024