kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-07-20 13:47:15 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(feishu): enhance #2791 with cardkit streaming + ASR fixes

Browse Source 
- rewrite streaming reply to official cardkit v2.0 API (default on, auto-fallback)
- fix Whisper hallucination: bump ASR sample rate to 16k, pass language=zh
- fix lock-over-IO and tmp file cleanup from #2791
- drop deprecated feishu_bot_name; quiet unknown-key warnings
- docs: cardkit permission and feishu_stream_reply usage
This commit is contained in:
zhayujie
2026-05-05 14:15:25 +08:00
parent 5080051e39
commit b80c3fe5a8
9 changed files with 304 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
voice/audio_convert.py
View File

@@ -79,7 +79,7 @@ def any_to_wav(any_path, wav_path):
audio = AudioSegment.from_file(any_path, parameters=["-nostdin"])
# AudioSegment 是不可变对象：set_frame_rate/set_channels 返回新对象，不修改原对象。
# 必须将返回值重新赋给 audio，否则修改不会生效。
audio = audio.set_frame_rate(8000) # 百度语音转写支持8000采样率, pcm_s16le, 单通道语音识别
audio = audio.set_frame_rate(16000)
audio = audio.set_channels(1)
audio.export(wav_path, format="wav", codec='pcm_s16le')