qwen-tts

import torch import soundfile as sf from qwen_tts.frontend import get_frontend from qwen_tts.models import QwenTTS # Define text and style for synthesis text = "Hello, this is a test from Qwen TTS, demonstrating speech synthesis." language = "en" style_name = "neutral" # Other options: 'happy', 'sad', etc. # Determine device for model loading (GPU if available, else CPU) device = 'cuda' if torch.cuda.is_available() else 'cpu' print(f"Attempting to load model on: {device}") # Load the QwenTTS model from Hugging Face Hub try: model = QwenTTS.from_pretrained('Qwen/Qwen3-TTS', device=device) except Exception as e: print(f"Failed to load model on {device}: {e}. Retrying with 'cpu'.") device = 'cpu' model = QwenTTS.from_pretrained('Qwen/Qwen3-TTS', device=device) # Initialize the frontend for text processing # The exp_name is retrieved from the loaded model's hyperparameters frontend = get_frontend(model.hparams.data.exp_name) # Get text and style tokens from the frontend text_token, style_token = frontend.get_text_token_and_style_token( text=text, language=language, style_name=style_name ) # Synthesize speech using the model output = model.synthesize(text_token, style_token) wav = output['wav'][0].cpu().numpy() # Extract waveform and move to CPU sampling_rate = model.hparams.data.sampling_rate # Save the synthesized audio to a WAV file output_filename = "qwen_tts_output.wav" sf.write(output_filename, wav, sampling_rate) print(f"Speech synthesized and saved to {output_filename}")