36 lines
1022 B
Python
36 lines
1022 B
Python
import time
|
|
import torch
|
|
import soundfile as sf
|
|
from qwen_tts import Qwen3TTSModel
|
|
|
|
# Load the model
|
|
model = Qwen3TTSModel.from_pretrained(
|
|
"Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice",
|
|
device_map="cuda:0",
|
|
dtype=torch.bfloat16,
|
|
)
|
|
print(model.get_supported_languages())
|
|
|
|
with open("input.txt", "r") as f:
|
|
text = f.read()
|
|
f.close()
|
|
|
|
# Generate speech with specific instructions
|
|
start_time = time.perf_counter()
|
|
wavs, sr = model.generate_custom_voice(
|
|
text=text,
|
|
language="English",
|
|
speaker="Aiden",
|
|
instruct="read the text in a calm and soothing voice, with a slight emphasis on key points, and maintain a steady pace throughout the narration.",
|
|
)
|
|
end_time = time.perf_counter()
|
|
|
|
# Save the generated audio
|
|
sf.write("output_custom_voice.wav", wavs[0], sr)
|
|
|
|
# Print timing
|
|
duration = end_time - start_time
|
|
audio_duration = len(wavs[0]) / sr
|
|
print(f"Generation time: {duration:.2f}s")
|
|
print(f"Audio duration: {audio_duration:.2f}s")
|
|
print(f"Real-time factor: {duration / audio_duration:.2f}x") |