Python:如何使用pyaudio for Google Cloud Speech API获取原始音频文件

pip install pyaudio

import pyaudio
import wave

# 设置音频参数
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
CHUNK = 1024
RECORD_SECONDS = 5
WAVE_OUTPUT_FILENAME = "output.wav"

# 初始化pyaudio
audio = pyaudio.PyAudio()

# 打开音频流
stream = audio.open(format=FORMAT, channels=CHANNELS,
                    rate=RATE, input=True,
                    frames_per_buffer=CHUNK)

print("开始录音...")

frames = []

# 录制音频
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
    data = stream.read(CHUNK)
    frames.append(data)

print("录音结束.")

# 停止音频流
stream.stop_stream()
stream.close()
audio.terminate()

# 保存音频文件
waveFile = wave.open(WAVE_OUTPUT_FILENAME, 'wb')
waveFile.setnchannels(CHANNELS)
waveFile.setsampwidth(audio.get_sample_size(FORMAT))
waveFile.setframerate(RATE)
waveFile.writeframes(b''.join(frames))
waveFile.close()

pip install google-cloud-speech

from google.cloud import speech_v1p1beta1 as speech

# 设置Google Cloud API密钥路径
key_path = 'path/to/your/key.json'

# 创建语音识别客户端
client = speech.SpeechClient.from_service_account_json(key_path)

# 读取音频文件
with open('output.wav', 'rb') as audio_file:
    content = audio_file.read()

# 构建音频配置
audio = speech.RecognitionAudio(content=content)
config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=16000,
    language_code='en-US'
)

# 发起语音识别请求
response = client.recognize(config=config, audio=audio)

# 处理识别结果
for result in response.results:
    print('识别结果: {}'.format(result.alternatives[0].transcript))