Failed Faster-Whisper task
I continue to get this error and I cant figure out whats going on, please help ❤️
Job submitted: 3f6a6e02-5249-4faf-9fb3-49ac501c695d-u2
Job failed: {'delayTime': 163, 'error': '{"error_type": "<class 'av.error.InvalidDataError'>", "error_message": "[Errno 1094995529] Invalid data found when processing input: '/tmp/tmpi89o0mcn.wav'", "error_traceback": "Traceback (most recent call last):\n File \"/usr/local/lib/python3.10/dist-packages/runpod/serverless/modules/rp_job.py\", line 134, in run_job\n handler_return = handler(job)\n File \"/usr/local/lib/python3.10/dist-packages/runpod/serverless/utils/rp_debugger.py\", line 165, in call\n result = self.function(*args, **kwargs)\n File \"/rp_handler.py\", line 72, in run_whisper_job\n whisper_results = MODEL.predict(\n File \"/predict.py\", line 75, in predict\n segments, info = list(model.transcribe(str(audio),\n File \"/usr/local/lib/python3.10/dist-packages/faster_whisper/transcribe.py\", line 277, in transcribe\n audio = decode_audio(audio, sampling_rate=sampling_rate)\n File \"/usr/local/lib/python3.10/dist-packages/faster_whisper/audio.py\", line 46, in decode_audio\n with av.open(input_file, metadata_errors=\"ignore\") as container:\n File \"av/container/core.pyx\", line 401, in av.container.core.open\n File \"av/container/core.pyx\", line 272, in av.container.core.Container.cinit\n File \"av/container/core.pyx\", line 292, in av.container.core.Container.err_check\n File \"av/error.pyx\", line 336, in av.error.err_check\nav.error.InvalidDataError: [Errno 1094995529] Invalid data found when processing input: '/tmp/tmpi89o0mcn.wav'\n", "hostname": "187psw4ygtfrrm-64410c48", "worker_id": "187psw4ygtfrrm", "runpod_version": "1.5.2"}', 'executionTime': 184, 'id': '3f6a6e02-5249-4faf-9fb3-49ac501c695d-u2', 'status': 'FAILED', 'workerId': '187psw4ygtfrrm'}
9 Replies
Invalid data found when processing input: '/tmp/tmpi89o0mcn.wav'\n",
meaning your audio isnt right, probably
try to search from that message
Its getting the audio directly from the browser source
okay
still it says something is wrong when processing it
maybe i'd suggest using other transport that's more reliable, or try with other audio files
Ive tried with multipule variation of audio files from different places
then maybe its your worker, if all audio files doesnt work with it
or your browser, your website
How can I check if its the worker
well debugging every step/ process
or just, start from the currently working worker, then make your changes one by one
@EgoDeath The prebuilt serverless endpoint for faster-whisper has an old version 0.10.0. You can try my latest test image that uses 1.1.1: https://discord.com/channels/912829806415085598/1356028626835079248/1356694401677529208
Thank you