Skip to content

ASR Pipeline - Giving File not found error when trying basic audio file extraction using ASR Pipeline #3373

@Josephcherian

Description

@Josephcherian

Bug

We are trying Docling extraction for audio/video files using ASR pipeline. When trying a basic code for extracting audio file by passing it as DocumentStream for DocumentConverter.convert() we are seeing error saying File not found. It seems the path being used is not proper.  The same seems to be working fine in case of other files like pdf and all.

Steps to reproduce

  1. Run the sample program attached.
Error seen
MLX Audio transcription has an error: Failed to load audio: ffmpeg version 8.1 Copyright (c) 2000-2026 the FFmpeg developers
  built with Apple clang version 21.0.0 (clang-2100.0.123.102)
  configuration: --prefix=/opt/homebrew/Cellar/ffmpeg/8.1_1 --enable-shared --enable-pthreads --enable-version3 --cc=clang --host-cflags= --host-ldflags= --enable-ffplay --enable-gpl --enable-libsvtav1 --enable-libopus --enable-libx264 --enable-libmp3lame --enable-libdav1d --enable-libvmaf --enable-libvpx --enable-libx265 --enable-openssl --enable-videotoolbox --enable-audiotoolbox --enable-neon
  libavutil      60. 26.100 / 60. 26.100
  libavcodec     62. 28.100 / 62. 28.100
  libavformat    62. 12.100 / 62. 12.100
  libavdevice    62.  3.100 / 62.  3.100
  libavfilter    11. 14.100 / 11. 14.100
  libswscale      9.  5.100 /  9.  5.100
  libswresample   6.  3.100 /  6.  3.100
[in#0 @ 0x8bf020000] Error opening input: No such file or directory
Error opening input file /Users/josephcherian/Documents/GitHub/datasift-opensource/harvard.wav.
Error opening input files: No such file or directory

Docling version

docling==2.86.0
docling-core==2.74.0

Python version

python3.12

Sample code tried

test_audio_video.py

Metadata

Metadata

Assignees

No one assigned

    Labels

    asrIssues related to ASR (Automatic Speech Recognition)bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions