|
|
import sounddevice as sd |
|
|
import soundfile as sf |
|
|
import sys |
|
|
import re |
|
|
|
|
|
TEXT_FILE = '/Users/jeqin/work/code/TestTranslator/test_data/text/test_asr_zh_with_index.txt' |
|
|
AUDIO_FOLDER= '/Users/jeqin/work/code/TestTranslator/test_data/recordings' |
|
|
SAMPLE_RATE = 16000 |
|
|
CHANNELS = 1 |
|
|
|
|
|
def get_lines_with_index(filepath): |
|
|
with open(filepath, encoding='utf-8') as f: |
|
|
for line in f: |
|
|
line = line.strip() |
|
|
m = re.match(r'^(\d+)\.\s*(.*)', line) |
|
|
if m: |
|
|
yield m.group(1), m.group(2) |
|
|
|
|
|
def record_audio(filename): |
|
|
import numpy as np |
|
|
def callback(indata, frames, time, status): |
|
|
recording.append(indata.copy()) |
|
|
|
|
|
while True: |
|
|
print("按回车开始录音...") |
|
|
input() |
|
|
print("正在录音，按回车结束录音，或输入 q 回车重新录音。") |
|
|
recording = [] |
|
|
stop = False |
|
|
|
|
|
with sd.InputStream(samplerate=SAMPLE_RATE, channels=CHANNELS, dtype='float32', callback=callback): |
|
|
user_input = input() |
|
|
if user_input.strip().lower() == 'q': |
|
|
print("重新录音...") |
|
|
stop = False |
|
|
continue |
|
|
else: |
|
|
stop = True |
|
|
|
|
|
if stop: |
|
|
audio_np = np.concatenate(recording, axis=0) |
|
|
max_val = np.max(np.abs(audio_np)) |
|
|
if max_val > 0: |
|
|
audio_np = audio_np * (0.99 / max_val) |
|
|
sf.write(f"{AUDIO_FOLDER}/{filename}", audio_np, SAMPLE_RATE) |
|
|
print(f"已保存: {filename}") |
|
|
break |
|
|
|
|
|
def main(): |
|
|
for idx, text in get_lines_with_index(TEXT_FILE): |
|
|
print(f"{idx}. {text}") |
|
|
if int(idx)==52: |
|
|
record_audio(f"{idx}.wav") |
|
|
|
|
|
if __name__ == '__main__': |
|
|
main() |
