File size: 6,990 Bytes
710db5f 9a005ca 1ca8bfc 9a005ca 710db5f 5034a0a 6f8989f 939d453 cabbcc5 6f8989f 8e1fa57 fc0b265 5034a0a d0fe6ef fc0b265 2399e19 8dc4fc2 9287297 710db5f b9fa8bc 710db5f b9fa8bc 710db5f b9fa8bc 710db5f b9fa8bc de83212 710db5f 0de4f47 b9fa8bc 0de4f47 b9fa8bc 0de4f47 b9fa8bc c1ab764 b9fa8bc de83212 710db5f ddfea13 710db5f |
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 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 |
import re
def timeformat_srt(time):
hours = time // 3600
minutes = (time - hours * 3600) // 60
seconds = time - hours * 3600 - minutes * 60
milliseconds = (time - int(time)) * 1000
return f"{int(hours):02d}:{int(minutes):02d}:{int(seconds):02d},{int(milliseconds):03d}"
def timeformat_txt(time):
hours = time // 3600
minutes = (time - hours * 3600) // 60
seconds = time - hours * 3600 - minutes * 60
#milliseconds = (time - int(time)) * 1000
if hours > 0:
return f"{int(hours):02d}:{int(minutes):02d}:{int(seconds):02d}"
else:
return f"{int(minutes):02d}:{int(seconds):02d}"
def timeformat_vtt(time):
hours = time // 3600
minutes = (time - hours * 3600) // 60
seconds = time - hours * 3600 - minutes * 60
milliseconds = (time - int(time)) * 1000
return f"{int(hours):02d}:{int(minutes):02d}:{int(seconds):02d}.{int(milliseconds):03d}"
def write_file(subtitle, output_file):
with open(output_file, 'w', encoding='utf-8') as f:
f.write(subtitle)
def get_srt(segments):
output = ""
for i, segment in enumerate(segments):
output += f"{i + 1}\n"
output += f"{timeformat_srt(segment['start'])} --> {timeformat_srt(segment['end'])}\n"
if segment['text'].startswith(' '):
segment['text'] = segment['text'][1:]
output += f"{segment['text']}\n\n"
return output
def get_csv(segments):
bDiarization = False
output = ""
# Check if speakers are identified
for i, segment in enumerate(segments):
if re.search(r'SPEAKER [0-9][0-9]: ',segment['text']) != None:
bDiarization = True
break
for i, segment in enumerate(segments):
if bDiarization:
speaker_id = ((segment['text']).split(":", 1)[0]).strip()
speaker_text = ((segment['text']).split(":", 1)[1]).strip()
output += f"{i + 1};{timeformat_srt(segment['start'])};{timeformat_srt(segment['end'])};{speaker_id};{speaker_text};\n"
else:
speaker_text = (segment['text']).strip()
output += f"{i + 1};{timeformat_srt(segment['start'])};{timeformat_srt(segment['end'])};{speaker_text};\n"
# Add titles to csv file
if bDiarization:
output = "Line;Start time;End time;Speaker;Text;\n" + output
else:
output = "Line;Start time;End time;Text;\n" + output
return output.rstrip("\n")
def get_vtt(segments):
output = "WebVTT\n\n"
for i, segment in enumerate(segments):
output += f"{i + 1}\n"
output += f"{timeformat_vtt(segment['start'])} --> {timeformat_vtt(segment['end'])}\n"
if segment['text'].startswith(' '):
segment['text'] = segment['text'][1:]
output += f"{segment['text']}\n\n"
return output
#def get_txt(segments):
# output = ""
# for i, segment in enumerate(segments):
# if segment['text'].startswith(' '):
# segment['text'] = segment['text'][1:]
# #output += f"{segment['text']}\n"
# output += f"{timeformat_txt(segment['start'])}\t{segment['text']}\n"
# return output
#def get_plaintext(segments):
# output = ""
# for i, segment in enumerate(segments):
# if segment['text'].startswith(' '):
# segment['text'] = segment['text'][1:]
# output += f"{segment['text']}\n"
# return output
def get_txt(segments):
bDiarization = False
output = ""
# Check if speakers are identified
for i, segment in enumerate(segments):
if re.search(r'SPEAKER [0-9][0-9]: ',segment['text']) != None:
bDiarization = True
break
for i, segment in enumerate(segments):
if bDiarization:
speaker_id = ((segment['text']).split(":", 1)[0]).strip()
speaker_text = ((segment['text']).split(":", 1)[1]).strip()
output += f"{timeformat_txt(segment['start'])}\t{speaker_id}\t{speaker_text}\n"
else:
speaker_text = (segment['text']).strip()
output += f"{timeformat_txt(segment['start'])}\t{speaker_text}\n"
return output
def get_plaintext(segments):
bDiarization = False
output = ""
# Check if speakers are identified
for i, segment in enumerate(segments):
if re.search(r'SPEAKER [0-9][0-9]: ',segment['text']) != None:
bDiarization = True
break
for i, segment in enumerate(segments):
if bDiarization:
speaker_id = ((segment['text']).split(":", 1)[0]).strip()
speaker_text = ((segment['text']).split(":", 1)[1]).strip()
output += f"{speaker_id}\t{speaker_text}\n"
else:
speaker_text = (segment['text']).strip()
output += f"{speaker_text}\n"
return output
def parse_srt(file_path):
"""Reads SRT file and returns as dict"""
with open(file_path, 'r', encoding='utf-8') as file:
srt_data = file.read()
data = []
blocks = srt_data.split('\n\n')
for block in blocks:
if block.strip() != '':
lines = block.strip().split('\n')
index = lines[0]
timestamp = lines[1]
sentence = ' '.join(lines[2:])
data.append({
"index": index,
"timestamp": timestamp,
"sentence": sentence
})
return data
def parse_vtt(file_path):
"""Reads WebVTT file and returns as dict"""
with open(file_path, 'r', encoding='utf-8') as file:
webvtt_data = file.read()
data = []
blocks = webvtt_data.split('\n\n')
for block in blocks:
if block.strip() != '' and not block.strip().startswith("WebVTT"):
lines = block.strip().split('\n')
index = lines[0]
timestamp = lines[1]
sentence = ' '.join(lines[2:])
data.append({
"index": index,
"timestamp": timestamp,
"sentence": sentence
})
return data
def get_serialized_srt(dicts):
output = ""
for dic in dicts:
output += f'{dic["index"]}\n'
output += f'{dic["timestamp"]}\n'
output += f'{dic["sentence"]}\n\n'
return output
def get_serialized_vtt(dicts):
output = "WebVTT\n\n"
for dic in dicts:
output += f'{dic["index"]}\n'
output += f'{dic["timestamp"]}\n'
output += f'{dic["sentence"]}\n\n'
return output
def safe_filename(name):
INVALID_FILENAME_CHARS = r'[<>:"/\\|?*\x00-\x1f]'
safe_name = re.sub(INVALID_FILENAME_CHARS, '_', name)
# Truncate the filename if it exceeds the max_length (20)
if len(safe_name) > 20:
file_extension = safe_name.split('.')[-1]
if len(file_extension) + 1 < 20:
truncated_name = safe_name[:20 - len(file_extension) - 1]
safe_name = truncated_name + '.' + file_extension
else:
safe_name = safe_name[:20]
return safe_name
|