From e823388753832180cae2671e29c24781781344bf Mon Sep 17 00:00:00 2001 From: YuanHui <31339626+alsesa@users.noreply.github.com> Date: Tue, 23 Dec 2025 10:32:28 +0800 Subject: [PATCH] fix transcribe error (cherry picked from commit 255cc192690654535c4ebeecec1ef6500943f42e) --- transcribe_media.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/transcribe_media.py b/transcribe_media.py index e770e05..b6fc7c5 100644 --- a/transcribe_media.py +++ b/transcribe_media.py @@ -1,5 +1,6 @@ import os import argparse +import uuid from funasr import AutoModel from funasr.utils.postprocess_utils import rich_transcription_postprocess @@ -11,8 +12,11 @@ from logging_config import setup_logging logger = setup_logging() -def extract_or_convert_audio(file_path, output_audio_path="processed_audio.wav"): +def extract_or_convert_audio(file_path, output_audio_path="processed_audio"): ext = os.path.splitext(file_path)[1].lower() + filename = os.path.basename(file_path) + random_uuid = str(uuid.uuid4()) + output_audio_path = output_audio_path + "_" + random_uuid + ".wav" if ext in [".mp4", ".mov", ".avi", ".mkv"]: logger.info("🎬 Extracting audio from video...") @@ -27,6 +31,7 @@ def extract_or_convert_audio(file_path, output_audio_path="processed_audio.wav") sound.export(output_audio_path, format="wav") else: raise ValueError(f"Unsupported file type: {ext}") + logger.info(f"Converted Audio saved to: {output_audio_path}") return output_audio_path @@ -152,8 +157,8 @@ def convert_media(file_path, is_batch=False, save_to_disk=True): logger.info(f"✅ Transcript saved to: {output_path}") return transcript finally: - if os.path.exists("processed_audio.wav"): - os.remove("processed_audio.wav") + if os.path.exists(audio_file): + os.remove(audio_file) def process_input(path, recursive=False):