t0is/transcriptor
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

cuda image

Browse Source
This commit is contained in:
t0is 2025-03-21 16:09:22 +01:00
parent 00a4ab1683
commit af9e579400
2 changed files with 5 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docker/transcriptor/Dockerfile
View File

@ -13,7 +13,7 @@ RUN add-apt-repository ppa:deadsnakes/ppa -y
# Install Python 3.9, python3.9-distutils, pip, and other dependencies # Install Python 3.9, python3.9-distutils, pip, and other dependencies
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y python3.9 python3.9-distutils python3-pip ffmpeg jq curl unzip libmariadb-dev gcc && \ apt-get install -y python3.9 python3.9-dev python3.9-distutils python3-pip ffmpeg jq curl unzip libmariadb-dev gcc && \
rm -rf /var/lib/apt/lists/* rm -rf /var/lib/apt/lists/*
# Set python3.9 as the default python3 and upgrade pip # Set python3.9 as the default python3 and upgrade pip

18
main.py
View File

@ -130,19 +130,6 @@ def download_vod(vod_url, output_filename):
subprocess.run(command, check=True) subprocess.run(command, check=True)
print(f"Downloaded VOD to {output_filename}") print(f"Downloaded VOD to {output_filename}")
def extract_audio(video_file, audio_file):
if os.path.exists(audio_file):
print(f"{audio_file} already exists. Skipping audio extraction.")
return
command = ["ffmpeg", "-i", video_file, "-vn", "-acodec", "mp3", audio_file, "-y"]
subprocess.run(command, check=True)
print(f"Extracted audio to {audio_file}")
def transcribe_audio(audio_file, model_name):
model = whisper.load_model(model_name, download_root="/app/models")
result = model.transcribe(audio_file, language=CHANNEL_LANGUAGE)
return result
def transcribe_audio_fast(audio_file, language, vod_id): def transcribe_audio_fast(audio_file, language, vod_id):
transcript_path = os.path.join(base_dirs["transcripts"], f"transcript_{vod_id}.json") transcript_path = os.path.join(base_dirs["transcripts"], f"transcript_{vod_id}.json")
@ -438,7 +425,7 @@ def db_set_transcription_finish(db, video_id):
""" """
cursor = db.cursor() cursor = db.cursor()
transcription_finish = datetime.now() transcription_finish = datetime.now()
query = f"UPDATE transcriptions SET transcription_finish = %s WHERE id = %s" query = f"UPDATE transcriptions SET transcription_finish = %s WHERE video_id = %s"
cursor.execute(query, (transcription_finish, video_id)) cursor.execute(query, (transcription_finish, video_id))
db.commit() db.commit()
cursor.close() cursor.close()
@ -511,6 +498,9 @@ def main():
handle_matches_fast(video, segments_data) handle_matches_fast(video, segments_data)
db_set_transcription_finish(db, video_id)
db_set_video_processed(db, video_id)
except Exception as e: except Exception as e:
print(f"Error processing video ID {video['id']}: {e}") print(f"Error processing video ID {video['id']}: {e}")
continue continue