Downloads · 30 days
5
22% of all-time downloads
whisper-small200sep4-es
jessicadiveai/whisper-small200sep4-es
whisper-small200sep4-es is a automatic speech recognition model from jessicadiveai. 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
23
Public
Parameters
242M
3.9 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
- Sep 5, 2024
- Updated
- Sep 5, 2024
- SHA
- f4ae3e20
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 Small 200 Sep 4 es - Jessica Martinez
This model is a fine-tuned version of openai/whisper-small on the procesar-videos2024rdm200 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5072
- Wer: 15.5020
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 25
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.276 | 4.1667 | 50 | 0.4263 | 19.2554 |
| 0.1108 | 8.3333 | 100 | 0.4481 | 16.7531 |
| 0.0397 | 12.5 | 150 | 0.4945 | 17.0278 |
| 0.0209 | 16.6667 | 200 | 0.5072 | 15.5020 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- es
- Created
- Sep 5, 2024
- Updated
- Sep 5, 2024