Audio-to-Audio
Transformers
Safetensors
dashengdenoiser
feature-extraction
signal-processing
custom_code
Instructions to use mispeech/dasheng-denoiser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/dasheng-denoiser with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mispeech/dasheng-denoiser", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Fix crash when last audio chunk has fewer frames than patch stride
Heinrich DinkelPad the last chunk to self.time_patches frames when it's shorter after splitting, preventing a RuntimeError in the Conv2d patch embedding when input is not a multiple of target_length.ec2e819
-
updated README
Heinrich Dinkel7a87364 -
Upload folder using huggingface_hub
Verified signaturee23a1f0 -
initial commit
Verified signaturec196738