Instructions to use Thomcles/Chatterbox-TTS-French with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use Thomcles/Chatterbox-TTS-French with Chatterbox:
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr) - Notebooks
- Google Colab
- Kaggle
Hyperparameters used in the training
#1
by Viewegger - opened
Hello,
may I ask you for how many epochs did you trained the model and what hyperparamters - lr rate etc. were used during the training?
Thank you!
Hello viewegger π,
Epochs: 1
Batch size: 8 (with gradient accumulation of 4)
Learning rate: 3e-5
Warmup steps: 2000
Evaluation: every 2000 steps (Consider the total number of samples, so you don't get just one or no evaluation)
hope this helps
Thank you - I just asked few more questions about the Korean model in the other repo!
Greatly appreciate the info!
Viewegger changed discussion status to closed