47 lines
1.3 KiB
Python
47 lines
1.3 KiB
Python
 
|
"""
|
||
|
|
Voice-editing demo using Tencent's AuK (https://github.com/Tencent-Hunyuan/AuK).
|
||
|
|
|
||
|
|
Unlike MOSS-TTS's `instruction` field (steers style at generation time),
|
||
|
|
AuK edits emotion on an *existing* recording directly - same speaker, same
|
||
|
|
words, same duration, different delivery. Demonstrates on the public-domain
|
||
|
|
narrator clip already used by the whisperx/tts demos.
|
||
|
|
|
||
|
|
Run from the auk/ directory with its .venv activated.
|
||
|
|
"""
|
||
|
|
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
from auk.infer.infer_auk import AukInfer, save_audio
|
||
|
|
|
||
|
|
HERE = Path(__file__).parent
|
||
|
|
CONFIG = HERE / "ckpts" / "AuK" / "config.yaml"
|
||
|
|
CKPT = HERE / "ckpts" / "AuK" / "auk_base.safetensors"
|
||
|
|
QWEN_PATH = HERE / "ckpts" / "Qwen2.5-Omni-3B"
|
||
|
|
INPUT_AUDIO = HERE.parent / "tts" / "reference" / "narrator_ref_en.wav"
|
||
|
|
OUTPUT_PATH = HERE / "narrator_excited.wav"
|
||
|
|
|
||
|
|
INSTRUCTION = "Change the emotion to excited."
|
||
|
|
|
||
|
|
|
||
|
|
def main() -> None:
|
||
|
|
engine = AukInfer(
|
||
|
|
str(CONFIG), str(CKPT), qwen_path=str(QWEN_PATH), cpu_offload=True
|
||
|
|
)
|
||
|
|
|
||
|
|
messages = [
|
||
|
|
{
|
||
|
|
"role": "user",
|
||
|
|
"content": [
|
||
|
|
{"type": "text", "text": INSTRUCTION},
|
||
|
|
{"type": "audio", "audio": str(INPUT_AUDIO)},
|
||
|
|
],
|
||
|
|
}
|
||
|
|
]
|
||
|
|
|
||
|
|
audio, sr = engine.generate(messages)
|
||
|
|
save_audio(audio, sr, str(OUTPUT_PATH))
|
||
|
|
print(f"[INFO] Saved {OUTPUT_PATH}")
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|