schihei
f00f29ab6b
- Created directory structure for prompts (system and user prompts) - Added specialized prompts for lectures, meetings, and interviews - Updated enhancer.py to load prompts from files - Added --prompt-type CLI parameter to select prompt type - Updated documentation and enhancement proposals
77 lines
2.8 KiB
Python
77 lines
2.8 KiB
Python
# Entry point for the mknotes audio transcription and note enhancement tool
|
|
|
|
import os
|
|
from tqdm import tqdm
|
|
|
|
from src.cli import parse_args
|
|
from src.utils import find_audio_files, ensure_directory_exists, convert_wav_to_mp3
|
|
from src.transcriber import transcribe_audio
|
|
from src.enhancer import enhance_note
|
|
|
|
def main():
|
|
args = parse_args()
|
|
input_dir = args.input_dir
|
|
output_dir = args.output_dir
|
|
model_size = args.model_size
|
|
|
|
ensure_directory_exists(output_dir)
|
|
|
|
audio_files = find_audio_files(input_dir)
|
|
if not audio_files:
|
|
print(f"No audio files found in {input_dir}.")
|
|
return
|
|
|
|
print(f"Found {len(audio_files)} audio files. Starting transcription and enhancement...")
|
|
|
|
for audio_path in tqdm(audio_files, desc="Processing files"):
|
|
base_name = os.path.splitext(os.path.basename(audio_path))[0]
|
|
txt_path = os.path.join(output_dir, base_name + ".txt")
|
|
md_path = os.path.join(output_dir, base_name + ".md")
|
|
|
|
# Skip if enhanced note already exists (unless force flag is set)
|
|
if os.path.exists(md_path) and not args.force:
|
|
print(f"Skipping {audio_path} - enhanced note already exists at {md_path}")
|
|
continue
|
|
|
|
# Check if transcription exists
|
|
if os.path.exists(txt_path) and not args.force:
|
|
print(f"Using existing transcription for {audio_path}")
|
|
with open(txt_path, "r", encoding="utf-8") as f:
|
|
transcription = f.read()
|
|
else:
|
|
# Convert WAV to MP3 if needed
|
|
path_to_transcribe = audio_path
|
|
|
|
if audio_path.lower().endswith(".wav"):
|
|
print(f"Processing WAV file: {audio_path}")
|
|
mp3_path = convert_wav_to_mp3(audio_path)
|
|
if mp3_path:
|
|
path_to_transcribe = mp3_path
|
|
else:
|
|
print(f"Warning: Failed to convert {audio_path}. Will attempt to transcribe the WAV file directly.")
|
|
|
|
# Transcribe audio
|
|
transcription = transcribe_audio(
|
|
path_to_transcribe,
|
|
txt_path,
|
|
model_size=model_size,
|
|
turbo=args.turbo
|
|
)
|
|
|
|
# Enhance note (only if md file doesn't exist or force flag is set)
|
|
if not os.path.exists(md_path) or args.force:
|
|
try:
|
|
enhanced_note = enhance_note(
|
|
transcription,
|
|
prompt_type=args.prompt_type
|
|
)
|
|
with open(md_path, "w", encoding="utf-8") as f:
|
|
f.write(enhanced_note)
|
|
except Exception as e:
|
|
print(f"Error enhancing note for {audio_path}: {e}")
|
|
|
|
print(f"Processing complete. Output saved to: {output_dir}")
|
|
|
|
if __name__ == "__main__":
|
|
main()
|