tts-600k-best

from qwen_tts.inference.qwen3_tts_model import Qwen3TTSModel

# Load the fine-tuned model
model = Qwen3TTSModel.from_pretrained(
    "./output/best",
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2"
)

# Generate speech with the new speaker
text = "Your text here"
ref_audio = "path/to/reference_audio.wav"

wavs, sr = model.generate_voice_clone(
    text=text,
    language="Auto",
    ref_audio=ref_audio,
    ref_text="Reference text for ICL mode",
    x_vector_only_mode=False
)