Downloads · 30 days
14
11% of all-time downloads
whisper-tiny-en-us
ykirpichev/whisper-tiny-en-us
whisper-tiny-en-us is a automatic speech recognition model from ykirpichev. 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
127
Public
Repo size
2.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin151 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 10, 2023
- Updated
- Jul 10, 2023
- SHA
- 611f1f64
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-tiny-en-us
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7061
- Wer Ortho: 0.3640
- Wer: 0.3542
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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 2.1622 | 1.79 | 50 | 0.9646 | 0.4510 | 0.3908 |
| 0.3628 | 3.57 | 100 | 0.5673 | 0.3812 | 0.3501 |
| 0.131 | 5.36 | 150 | 0.5827 | 0.3714 | 0.3436 |
| 0.0488 | 7.14 | 200 | 0.6058 | 0.3689 | 0.3383 |
| 0.0144 | 8.93 | 250 | 0.6444 | 0.3671 | 0.3430 |
| 0.0044 | 10.71 | 300 | 0.6652 | 0.3418 | 0.3282 |
| 0.0021 | 12.5 | 350 | 0.6827 | 0.3405 | 0.3306 |
| 0.0013 | 14.29 | 400 | 0.6956 | 0.3448 | 0.3341 |
| 0.0011 | 16.07 | 450 | 0.7061 | 0.3640 | 0.3542 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jul 10, 2023
- Updated
- Jul 10, 2023