Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Updated deps and switch from youtube-dl to yt-dlp #6

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Updated deps and switch from youtube-dl to yt-dlp #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,19 +14,19 @@
author_email="[email protected]",
license="MIT",
install_requires=[
"librosa==0.7.2",
"youtube-dl",
"librosa>=0.7.2",
"yt-dlp",
"tqdm",
"pandas",
"pydub",
"scikit-learn==0.19.2",
"scikit-learn>=0.19.2",
"webrtcvad",
"scipy>=1.0.0",
"numba==0.48",
"numba>=0.48",
"inflect",
"numpy>=1.14.0",
"unidecode==0.4.20",
"vtt_to_srt3",
"unidecode>=0.4.20",
"vtt_to_srt3==0.1.8.9",
"youtube-transcript-api>=0.4.1"
],
packages=["youtube_tts_data_generator"],
Expand Down
30 changes: 23 additions & 7 deletions youtube_tts_data_generator/youtube_tts_data_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import youtube_dl
import yt_dlp
import os
import errno
import warnings
Expand All @@ -21,6 +21,8 @@
import re
from vtt_to_srt.vtt_to_srt import read_text_file, convert_content

import soundfile as sf


class NoSubtitleWarning(UserWarning):
pass
Expand Down Expand Up @@ -301,15 +303,13 @@ def download(self, links_txt):
for ix in range(len(links)):
link = links[ix]
video_id = self.get_video_id(link)

if video_id != []:
filename = f"{self.name}{ix+1}.mp4"
wav_file = filename.replace(".mp4", ".wav")
self.ydl_opts["outtmpl"] = os.path.join(
self.download_dir, filename
)

with youtube_dl.YoutubeDL(self.ydl_opts) as ydl:
with yt_dlp.YoutubeDL(self.ydl_opts) as ydl:
try:
trans = (
YouTubeTranscriptApi.list_transcripts(video_id)
Expand All @@ -330,6 +330,7 @@ def download(self, links_txt):
),
),
"w",
encoding="utf-8",
).write(json_formatted)
ydl.download([link])
print(
Expand All @@ -345,15 +346,18 @@ def download(self, links_txt):
f"WARNING - video {link} does not have subtitles. Skipping..",
NoSubtitleWarning,
)

for root, dirs, fns in os.walk(self.download_dir):
for fn in fns:
if wav_file and ".mp4" in fn:
os.replace(self.download_dir + "\\" + filename + ".wav", self.download_dir + "\\" + wav_file)
del self.ydl_opts["outtmpl"]
else:
warnings.warn(
f"WARNING - video {link} does not seem to be a valid YouTube url. Skipping..",
InvalidURLWarning,
)
if self.wav_filenames != []:
with open(self.filenames_txt, "w") as f:
with open(self.filenames_txt, "w", encoding="utf-8") as f:
lines = "filename,subtitle,trim_mins_begin,trim_mins_end\n"
for wav in self.wav_filenames:
lines += f"{wav},{wav.replace('.wav','')}.{self.dataset_lang}.json,0,0\n"
Expand Down Expand Up @@ -738,9 +742,21 @@ def finalize_dataset(self, min_audio_length=5, max_audio_length=14):
and trimmed_length <= max_audio_length
):
self.len_dataset += trimmed_length
"""
librosa.output.write_wav(
os.path.join(self.dest_dir, "wavs", audio), silence_removed, sr
os.path.join(self.dest_dir, "wavs", audio),
silence_removed,
sr
)
"""
sf.write(
os.path.join(self.dest_dir, "wavs", audio),
silence_removed,
sr,
format='wav',
subtype='PCM_16'
)

filtered_audios.append(audio)
filtered_txts.append(audio.replace(".wav", ".txt"))

Expand Down