Files
CyberGril/experiments/hel715/livetalking-patch/cosyvoice.py
T

70 lines
2.6 KiB
Python

import time
import numpy as np
import resampy
import requests
from io import BytesIO
from typing import Iterator
from utils.logger import logger
from .base_tts import BaseTTS, State
from registry import register
@register("tts", "cosyvoice")
class CosyVoiceTTS(BaseTTS):
"""适配本机既有 CosyVoice3 流式 TTS (POST /tts -> 24kHz int16 PCM 流)."""
def txt_to_audio(self, msg: tuple[str, dict]):
text, textevent = msg
voice = textevent.get('tts', {}).get('voice', self.opt.REF_FILE or 'default')
self.stream_tts(self.cosyvoice(text, voice), msg)
def cosyvoice(self, text: str, voice: str) -> Iterator[bytes]:
start = time.perf_counter()
try:
res = requests.post(
f"{self.opt.TTS_SERVER}/tts",
json={"text": text, "voice": voice},
stream=True,
timeout=(5, 300),
)
if res.status_code != 200:
logger.error("cosyvoice http %s: %s", res.status_code, res.text[:200])
return
first = True
for chunk in res.iter_content(chunk_size=4800): # 100ms @24k int16
if first:
logger.info("cosyvoice time to first chunk: %.3fs", time.perf_counter() - start)
first = False
if chunk and self.state == State.RUNNING:
yield chunk
elif self.state != State.RUNNING:
logger.info("cosyvoice interrupted, stop consuming")
res.close()
return
except Exception:
logger.exception('cosyvoice tts error')
def stream_tts(self, audio_stream: Iterator[bytes], msg: tuple[str, dict]):
text, textevent = msg
first = True
for chunk in audio_stream:
if not chunk:
continue
pcm24 = np.frombuffer(chunk, dtype=np.int16).astype(np.float32) / 32767.0
stream = resampy.resample(pcm24, sr_orig=24000, sr_new=self.sample_rate)
streamlen = stream.shape[0]
idx = 0
while streamlen >= self.chunk:
eventpoint = {}
if first:
eventpoint = {'status': 'start', 'text': text}
first = False
eventpoint.update(**textevent)
self.parent.put_audio_frame(stream[idx:idx + self.chunk], eventpoint)
streamlen -= self.chunk
idx += self.chunk
eventpoint = {'status': 'end', 'text': text}
eventpoint.update(**textevent)
self.parent.put_audio_frame(np.zeros(self.chunk, np.float32), eventpoint)