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")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pyp1/VoiceCraft", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload gigaHalfLibri330M_TTSEnhanced_max16s.pth
Browse filesThis 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 <= 16sec
gigaHalfLibri330M_TTSEnhanced_max16s.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0ce2d8208efbae2120fd577daaaea9d96818ab7cb9b6c3a2b75ccc3a0f48e0f
|
| 3 |
+
size 1293936129
|