kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-06-02 00:57:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

百度语音转写支持8000采样率, pcm_s16le编码, 单通道语音的组合

Browse Source
This commit is contained in:
FMStereo
2024-01-18 12:46:18 +08:00
parent eae95dfef5
commit 977d3bc02e
2 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
voice/audio_convert.py
View File

@@ -64,7 +64,9 @@ def any_to_wav(any_path, wav_path):
if any_path.endswith(".sil") or any_path.endswith(".silk") or any_path.endswith(".slk"): if any_path.endswith(".sil") or any_path.endswith(".silk") or any_path.endswith(".slk"):
return sil_to_wav(any_path, wav_path) return sil_to_wav(any_path, wav_path)
audio = AudioSegment.from_file(any_path) audio = AudioSegment.from_file(any_path)
audio.export(wav_path, format="wav") 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.set_channels(1)
audio.export(wav_path, format="wav", codec='pcm_s16le')
def any_to_sil(any_path, sil_path): def any_to_sil(any_path, sil_path):

2
voice/baidu/baidu_voice.py
View File

@@ -62,7 +62,7 @@ class BaiduVoice(Voice):
# 识别本地文件 # 识别本地文件
logger.debug("[Baidu] voice file name={}".format(voice_file)) logger.debug("[Baidu] voice file name={}".format(voice_file))
pcm = get_pcm_from_wav(voice_file) pcm = get_pcm_from_wav(voice_file)
res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.dev_id}) res = self.client.asr(pcm, "pcm", 8000, {"dev_pid": self.dev_id})
if res["err_no"] == 0: if res["err_no"] == 0:
logger.info("百度语音识别到了：{}".format(res["result"])) logger.info("百度语音识别到了：{}".format(res["result"]))
text = "".join(res["result"]) text = "".join(res["result"])