Text-to-Speech
Transformers
Safetensors
English
German
moss_tts_local
feature-extraction
moss-tts
moss-tts-local
voice-acting
expressive-tts
vocal-bursts
48khz
custom_code
Instructions to use laion/moss-tts-local-transformer-4.55b-voice-acting-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use laion/moss-tts-local-transformer-4.55b-voice-acting-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="laion/moss-tts-local-transformer-4.55b-voice-acting-v2", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("laion/moss-tts-local-transformer-4.55b-voice-acting-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
v2: best checkpoint (further FT on synthetic Best-of-N data) + inference code + processor
b8904c5 verified - Xet hash:
- 0de943a9e2252a7385036759d4a182d34a22682c0a077d0107788aa60cc8f97f
- Size of remote file:
- 8.26 GB
- SHA256:
- dec264542f015f59475c40f13f01ca6c25627eb518d52f7089a4d89874c5d3a4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.