From 27660f48e47964c60fb82f4a5fb30f9a7c29b8af Mon Sep 17 00:00:00 2001 From: Accusys Date: Mon, 6 Jul 2026 14:23:53 +0800 Subject: [PATCH] fix: ASRX fallback to ASR segments on error instead of silent_audio When ASRX processing fails (error or exception), it now falls back to ASR segments instead of returning silent_audio with 0 segments. This ensures asrx_segments >= asr_segments always, fixing the bug where ASRX would report 0 segments even when ASR detected speech. --- scripts/asrx_processor.py | 60 +++++++++++++++++++++++++++++++++------ 1 file changed, 52 insertions(+), 8 deletions(-) diff --git a/scripts/asrx_processor.py b/scripts/asrx_processor.py index 3f18d5c..c46f9ae 100755 --- a/scripts/asrx_processor.py +++ b/scripts/asrx_processor.py @@ -228,10 +228,21 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "", if "error" in result: if publisher: publisher.error("asrx", result["error"]) - output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} + # Fallback to ASR segments if ASRX fails but ASR has content + if asr_segments: + print(f"[ASRX] Resume error, falling back to {len(asr_segments)} ASR segments", file=sys.stderr) + output_result = { + "status": "has_transcript", + "language": None, + "segments": [{"start_time": s["start"], "end_time": s["end"], "text": s["text"], "speaker_id": "SPEAKER_0"} for s in asr_segments], + "segment_count": len(asr_segments), + "fallback_from_asr": True, + } + else: + output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} _atomic_write(output_path, output_result) if publisher: - publisher.complete("asrx", "0 segments") + publisher.complete("asrx", f"{output_result['segment_count']} segments") _cleanup(tmp_dir) return output_result @@ -264,10 +275,21 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "", publisher.error("asrx", str(e)) import traceback traceback.print_exc() - output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} + # Fallback to ASR segments if ASRX fails but ASR has content + if asr_segments: + print(f"[ASRX] Resume exception, falling back to {len(asr_segments)} ASR segments", file=sys.stderr) + output_result = { + "status": "has_transcript", + "language": None, + "segments": [{"start_time": s["start"], "end_time": s["end"], "text": s["text"], "speaker_id": "SPEAKER_0"} for s in asr_segments], + "segment_count": len(asr_segments), + "fallback_from_asr": True, + } + else: + output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} _atomic_write(output_path, output_result) if publisher: - publisher.complete("asrx", "0 segments") + publisher.complete("asrx", f"{output_result['segment_count']} segments") _cleanup(tmp_dir) return output_result @@ -328,10 +350,21 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "", if "error" in result: if publisher: publisher.error("asrx", result["error"]) - output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} + # Fallback to ASR segments if ASRX fails + if asr_segments: + print(f"[ASRX] ASRX failed, falling back to {len(asr_segments)} ASR segments", file=sys.stderr) + output_result = { + "status": "has_transcript", + "language": None, + "segments": [{"start_time": s["start"], "end_time": s["end"], "text": s["text"], "speaker_id": "SPEAKER_0"} for s in asr_segments], + "segment_count": len(asr_segments), + "fallback_from_asr": True, + } + else: + output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} _atomic_write(output_path, output_result) if publisher: - publisher.complete("asrx", "0 segments") + publisher.complete("asrx", f"{output_result['segment_count']} segments") _cleanup(tmp_dir) return output_result @@ -359,10 +392,21 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "", import traceback traceback.print_exc() - output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} + # Fallback to ASR segments if ASRX fails but ASR has content + if asr_segments: + print(f"[ASRX] Exception occurred, falling back to {len(asr_segments)} ASR segments", file=sys.stderr) + output_result = { + "status": "has_transcript", + "language": None, + "segments": [{"start_time": s["start"], "end_time": s["end"], "text": s["text"], "speaker_id": "SPEAKER_0"} for s in asr_segments], + "segment_count": len(asr_segments), + "fallback_from_asr": True, + } + else: + output_result = {"status": "silent_audio", "language": None, "segments": [], "segment_count": 0} _atomic_write(output_path, output_result) if publisher: - publisher.complete("asrx", "0 segments") + publisher.complete("asrx", f"{output_result['segment_count']} segments") # 如果 checkpoint 已存在（Step 3 完成後 crash），保留 WAV 給 resume if not os.path.exists(checkpoint_path): _cleanup(tmp_dir)