amanuelbyte
/

chatterbox-fr-lora

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Chatterbox FR LoRA Fine-Tuned Model

Fine-tuned Chatterbox Multilingual TTS for French voice cloning.

Training Details

Base model: ChatterboxMultilingualTTS
Method: LoRA (rank=32, alpha=64.0)
Dataset: amanuelbyte/acl-voice-cloning-fr-expandedtry (20% stratified sample)
Epochs: 3
Best val loss: 2.6505
Language: French (fr)
Cloning mode: cross_lingual

Files

final_lora_adapter.pt - LoRA weights from last step
best_lora_adapter.pt - LoRA weights from best validation loss
merged_model/t3_mtl23ls_v2.pt - Full merged T3 model weights
samples/ - Generated audio samples for comparison

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support