# TTS Model Directory

This directory should contain the Qwen3-TTS fine-tuned voice model.

The model files are not included in git due to size (~7.8GB).

## Required Files

Place the following files here:
- config.json
- generation_config.json
- model.safetensors (main model weights)
- tokenizer_config.json
- vocab.json
- merges.txt
- preprocessor_config.json
- speech_tokenizer/ (subdirectory with tokenizer files)

## Model Source

The model was fine-tuned using qwen-tts with custom speaker embeddings.
