github/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-03-18 12:40:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

formatting: run precommit on all files

Browse Source
This commit is contained in:
lanvent
2023-04-22 12:01:29 +08:00
parent eaf4e9174f
commit 618c94edb8
40 changed files with 229 additions and 647 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
voice/audio_convert.py
View File

@@ -33,6 +33,7 @@ def get_pcm_from_wav(wav_path):
wav = wave.open(wav_path, "rb")
return wav.readframes(wav.getnframes())
def any_to_mp3(any_path, mp3_path):
"""
把任意格式转成mp3文件
@@ -40,16 +41,13 @@ def any_to_mp3(any_path, mp3_path):
if any_path.endswith(".mp3"):
shutil.copy2(any_path, mp3_path)
return
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"):
sil_to_wav(any_path, any_path)
any_path = mp3_path
audio = AudioSegment.from_file(any_path)
audio.export(mp3_path, format="mp3")
def any_to_wav(any_path, wav_path):
"""
把任意格式转成wav文件
@@ -57,11 +55,7 @@ def any_to_wav(any_path, wav_path):
if any_path.endswith(".wav"):
shutil.copy2(any_path, wav_path)
return
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)
audio = AudioSegment.from_file(any_path)
audio.export(wav_path, format="wav")
@@ -71,11 +65,7 @@ def any_to_sil(any_path, sil_path):
"""
把任意格式转成sil文件
"""
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"):
shutil.copy2(any_path, sil_path)
return 10000
audio = AudioSegment.from_file(any_path)

42
voice/azure/azure_voice.py
View File

@@ -40,57 +40,33 @@ class AzureVoice(Voice):
config = json.load(fr)
self.api_key = conf().get("azure_voice_api_key")
self.api_region = conf().get("azure_voice_region")
self.speech_config = speechsdk.SpeechConfig(
subscription=self.api_key, region=self.api_region
)
self.speech_config.speech_synthesis_voice_name = config[
"speech_synthesis_voice_name"
]
self.speech_config.speech_recognition_language = config[
"speech_recognition_language"
]
self.speech_config = speechsdk.SpeechConfig(subscription=self.api_key, region=self.api_region)
self.speech_config.speech_synthesis_voice_name = config["speech_synthesis_voice_name"]
self.speech_config.speech_recognition_language = config["speech_recognition_language"]
except Exception as e:
logger.warn("AzureVoice init failed: %s, ignore " % e)
def voiceToText(self, voice_file):
audio_config = speechsdk.AudioConfig(filename=voice_file)
speech_recognizer = speechsdk.SpeechRecognizer(
speech_config=self.speech_config, audio_config=audio_config
)
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=self.speech_config, audio_config=audio_config)
result = speech_recognizer.recognize_once()
if result.reason == speechsdk.ResultReason.RecognizedSpeech:
logger.info(
"[Azure] voiceToText voice file name={} text={}".format(
voice_file, result.text
)
)
logger.info("[Azure] voiceToText voice file name={} text={}".format(voice_file, result.text))
reply = Reply(ReplyType.TEXT, result.text)
else:
logger.error(
"[Azure] voiceToText error, result={}, canceldetails={}".format(
result, result.cancellation_details
)
)
logger.error("[Azure] voiceToText error, result={}, canceldetails={}".format(result, result.cancellation_details))
reply = Reply(ReplyType.ERROR, "抱歉，语音识别失败")
return reply
def textToVoice(self, text):
fileName = TmpDir().path() + "reply-" + str(int(time.time())) + ".wav"
audio_config = speechsdk.AudioConfig(filename=fileName)
speech_synthesizer = speechsdk.SpeechSynthesizer(
speech_config=self.speech_config, audio_config=audio_config
)
speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=self.speech_config, audio_config=audio_config)
result = speech_synthesizer.speak_text(text)
if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
logger.info(
"[Azure] textToVoice text={} voice file name={}".format(text, fileName)
)
logger.info("[Azure] textToVoice text={} voice file name={}".format(text, fileName))
reply = Reply(ReplyType.VOICE, fileName)
else:
logger.error(
"[Azure] textToVoice error, result={}, canceldetails={}".format(
result, result.cancellation_details
)
)
logger.error("[Azure] textToVoice error, result={}, canceldetails={}".format(result, result.cancellation_details))
reply = Reply(ReplyType.ERROR, "抱歉，语音合成失败")
return reply

4
voice/baidu/baidu_voice.py
View File

@@ -85,9 +85,7 @@ class BaiduVoice(Voice):
fileName = TmpDir().path() + "reply-" + str(int(time.time())) + ".mp3"
with open(fileName, "wb") as f:
f.write(result)
logger.info(
"[Baidu] textToVoice text={} voice file name={}".format(text, fileName)
)
logger.info("[Baidu] textToVoice text={} voice file name={}".format(text, fileName))
reply = Reply(ReplyType.VOICE, fileName)
else:
logger.error("[Baidu] textToVoice error={}".format(result))

10
voice/google/google_voice.py
View File

@@ -24,11 +24,7 @@ class GoogleVoice(Voice):
audio = self.recognizer.record(source)
try:
text = self.recognizer.recognize_google(audio, language="zh-CN")
logger.info(
"[Google] voiceToText text={} voice file name={}".format(
text, voice_file
)
)
logger.info("[Google] voiceToText text={} voice file name={}".format(text, voice_file))
reply = Reply(ReplyType.TEXT, text)
except speech_recognition.UnknownValueError:
reply = Reply(ReplyType.ERROR, "抱歉，我听不懂")
@@ -42,9 +38,7 @@ class GoogleVoice(Voice):
mp3File = TmpDir().path() + "reply-" + str(int(time.time())) + ".mp3"
tts = gTTS(text=text, lang="zh")
tts.save(mp3File)
logger.info(
"[Google] textToVoice text={} voice file name={}".format(text, mp3File)
)
logger.info("[Google] textToVoice text={} voice file name={}".format(text, mp3File))
reply = Reply(ReplyType.VOICE, mp3File)
except Exception as e:
reply = Reply(ReplyType.ERROR, str(e))

6
voice/openai/openai_voice.py
View File

@@ -22,11 +22,7 @@ class OpenaiVoice(Voice):
result = openai.Audio.transcribe("whisper-1", file)
text = result["text"]
reply = Reply(ReplyType.TEXT, text)
logger.info(
"[Openai] voiceToText text={} voice file name={}".format(
text, voice_file
)
)
logger.info("[Openai] voiceToText text={} voice file name={}".format(text, voice_file))
except Exception as e:
reply = Reply(ReplyType.ERROR, str(e))
finally:

12
voice/pytts/pytts_voice.py
View File

@@ -5,6 +5,7 @@ pytts voice service (offline)
import os
import sys
import time
import pyttsx3
from bridge.reply import Reply, ReplyType
@@ -12,6 +13,7 @@ from common.log import logger
from common.tmp_dir import TmpDir
from voice.voice import Voice
class PyttsVoice(Voice):
engine = pyttsx3.init()
@@ -20,7 +22,7 @@ class PyttsVoice(Voice):
self.engine.setProperty("rate", 125)
# 音量
self.engine.setProperty("volume", 1.0)
if sys.platform == 'win32':
if sys.platform == "win32":
for voice in self.engine.getProperty("voices"):
if "Chinese" in voice.name:
self.engine.setProperty("voice", voice.id)
@@ -33,23 +35,23 @@ class PyttsVoice(Voice):
def textToVoice(self, text):
try:
# avoid the same filename
wavFileName = "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7fffffff) + ".wav"
wavFileName = "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".wav"
wavFile = TmpDir().path() + wavFileName
logger.info("[Pytts] textToVoice text={} voice file name={}".format(text, wavFile))
self.engine.save_to_file(text, wavFile)
if sys.platform == 'win32':
if sys.platform == "win32":
self.engine.runAndWait()
else:
# In ubuntu, runAndWait do not really wait until the file created.
# In ubuntu, runAndWait do not really wait until the file created.
# It will return once the task queue is empty, but the task is still running in coroutine.
# And if you call runAndWait() and time.sleep() twice, it will stuck, so do not use this.
# If you want to fix this, add self._proxy.setBusy(True) in line 127 in espeak.py, at the beginning of the function save_to_file.
# self.engine.runAndWait()
# Before espeak fix this problem, we iterate the generator and control the waiting by ourself.
# But this is not the canonical way to use it, for example if the file already exists it also cannot wait.
# But this is not the canonical way to use it, for example if the file already exists it also cannot wait.
self.engine.iterate()
while self.engine.isBusy() or wavFileName not in os.listdir(TmpDir().path()):
time.sleep(0.1)