File size: 2,636 Bytes
8a3bc32 8a27f7c 8a3bc32 8a27f7c 8a3bc32 8a27f7c 8a3bc32 8a27f7c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import os
import csv
import wave
import re
def add_text_index():
text_file = '../tests/test_data/text/test_asr_zh.txt'
index = 1
with open(text_file, encoding='utf-8') as f:
for line in f:
line = line.strip()
# print(line)
if not line:
continue
if line.startswith('#'):
# print(line)
continue
line = f"{index}. {line}"
print(line)
index += 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 get_wav_length(wav_path):
try:
with wave.open(wav_path, 'rb') as wf:
frames = wf.getnframes()
rate = wf.getframerate()
duration = frames / float(rate)
return duration
except Exception as e:
print(f"Error reading {wav_path}: {e}")
return 0
def write_csv(rows, output_csv):
with open(output_csv, 'w', newline='', encoding='utf-8') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(['序号', '文本', '音频长度(秒)'])
writer.writerows(rows)
def print_text_and_audio_length():
text_file = '../tests/test_data/text/test_asr_zh_with_index.txt'
audio_folder = '../tests/test_data/recordings'
output_csv = 'csv/text_audio_length.csv'
rows = []
for idx, text in get_lines_with_index(text_file):
# print(idx)
# print(text)
audio_path = os.path.join(audio_folder, f"{idx}.wav")
audio_length = get_wav_length(audio_path)
audio_length = round(audio_length, 2) if audio_length is not None else None
# print(audio_length)
rows.append([idx, text, round(audio_length,2)])
write_csv(rows, output_csv)
def get_text_distance(text1, text2):
from lib.utils import run_textdistance, clean_text_for_comparison_zh, highlight_diff
text1_clean = clean_text_for_comparison_zh(text1)
text2_clean = clean_text_for_comparison_zh(text2)
d, nd = run_textdistance(text1_clean, text2_clean)
diff = highlight_diff(text1_clean, text2_clean, spliter="")
return d, nd, diff
def get_origin_text_dict():
text_file = '../tests/test_data/text/test_asr_zh_with_index.txt'
text_dict = {}
for idx, text in get_lines_with_index(text_file):
text_dict[idx] = text
return text_dict
if __name__ == '__main__':
# add_text_index()
print_text_and_audio_length()
# pass |