Downloads · 30 days
22
1% of all-time downloads
kid-whisper-medium-en-myst_cslu
aadel4/kid-whisper-medium-en-myst_cslu
kid-whisper-medium-en-myst_cslu is a automatic speech recognition model from aadel4. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of openai/whisper-medium-en on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.22987066209316254 - Wer: 7.945455976651671
All-time downloads
1.8K
Public
Repo size
12.2 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.pt6.1 GB · 67%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 20, 2023
- Updated
- Apr 9, 2024
- SHA
- f6dd9498
Model card
From the Hugging Face model README
openai/whisper-medium-en
This model is a fine-tuned version of openai/whisper-medium-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.22987066209316254
- Wer: 7.945455976651671`
Training and evaluation data
- Training data: Myst Train (125 hours) + CSLU Scripted train (35 hours)
- Evaluation data: Myst Dev (20.9 hours) + CSLU Scripted Dev(4.8)
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- 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
- training_steps: 10000
- converged_after: 1000
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Sep 20, 2023
- Updated
- Apr 9, 2024