Downloads · 30 days
12
0% of all-time downloads
whisper-small-atcosim
jlvdoorn/whisper-small-atcosim
whisper-small-atcosim is a automatic speech recognition model from jlvdoorn. 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
4.3K
Public
Parameters
242M
9.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jan 9, 2024
- Updated
- Jan 12, 2024
- SHA
- e4b92341
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-atcosim
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0569
- Wer: 1.5420
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1664 | 8.33 | 500 | 0.0441 | 1.4632 |
| 0.0008 | 16.67 | 1000 | 0.0465 | 1.5420 |
| 0.0001 | 25.0 | 1500 | 0.0494 | 1.5142 |
| 0.0 | 33.33 | 2000 | 0.0511 | 1.5049 |
| 0.0 | 41.67 | 2500 | 0.0524 | 1.5003 |
| 0.0 | 50.0 | 3000 | 0.0535 | 1.5142 |
| 0.0 | 58.33 | 3500 | 0.0544 | 1.5188 |
| 0.0 | 66.67 | 4000 | 0.0552 | 1.5188 |
| 0.0 | 75.0 | 4500 | 0.0559 | 1.5327 |
| 0.0 | 83.33 | 5000 | 0.0564 | 1.5558 |
| 0.0 | 91.67 | 5500 | 0.0567 | 1.5512 |
| 0.0 | 100.0 | 6000 | 0.0569 | 1.5420 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jan 9, 2024
- Updated
- Jan 12, 2024