Instructions to use pyp1/VoiceCraft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pyp1/VoiceCraft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="pyp1/VoiceCraft")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pyp1/VoiceCraft", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Upload encodec_8cb1024_giga.th
Verified signature52b0f90
-
Upload 830M_TTSEnhanced.pth
Verified signature6009034
-
Upload 330M_TTSEnhanced.pth
Verified signaturee48e273
-
Push model using huggingface_hub.
Verified signature9958d8f
-
Upload gigaHalfLibri330M_TTSEnhanced_max16s.pth
Verified signatureThis model is finetuned from the giga330M model with the TTS objective on a combination of gigaspeech and 1/5 of librilight (due to storage constraint). The longest training utterance is 16 seconds, so inference should only work for those sentences where prompt + genration <= 16seca885d77 -
Update README.md
Verified signature031de3a
-
upload the correct 330M model
Verified signature874def2
-
upload the correct 830M model
Verified signaturea525dd8 -
Upload giga830M.pth
Verified signaturef640828 -
upload giga330M.pth
Verified signature330M is just as good as 830M, but way faster5862c88
-
Upload encodec_4cb2048_giga.th
Verified signature96bcb93 -
initial commit
Verified signature8e1ef51