Text-to-Speech
Transformers
Safetensors
PyTorch
English
Chinese
breeze
text-generation
speech-generation
voice-clone
voice-design
voice-direction
cuda
Instructions to use BreezeBlue/Breeze-TTS-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BreezeBlue/Breeze-TTS-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="BreezeBlue/Breeze-TTS-2")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("BreezeBlue/Breeze-TTS-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Audio glitches
#16
by sirovub - opened
I did a few tests runs through the spaces demo. Both times the audio glitched. One has some pop sound near the end and other has garbled audio.
The text was: 'You go back and enjoy yourself.'
How to avoid it? Is it the default setting of 4 for Classifier-Free Guidance in the space causing it or something else?
I realized huggingface reencoded the audios on upload so the pop went away.
sirovub changed discussion status to closed