Recherche avancée
Autres articles (89)
-
Les autorisations surchargées par les plugins
27 avril 2010, parMediaspip core
autoriser_auteur_modifier() afin que les visiteurs soient capables de modifier leurs informations sur la page d’auteurs -
Des sites réalisés avec MediaSPIP
2 mai 2011, parCette page présente quelques-uns des sites fonctionnant sous MediaSPIP.
Vous pouvez bien entendu ajouter le votre grâce au formulaire en bas de page. -
Encoding and processing into web-friendly formats
13 avril 2011, parMediaSPIP automatically converts uploaded files to internet-compatible formats.
Video files are encoded in MP4, Ogv and WebM (supported by HTML5) and MP4 (supported by Flash).
Audio files are encoded in MP3 and Ogg (supported by HTML5) and MP3 (supported by Flash).
Where possible, text is analyzed in order to retrieve the data needed for search engine detection, and then exported as a series of image files.
All uploaded files are stored online in their original format, so you can (...)
Sur d’autres sites (11413)
-
Why does a command in my Bash-script return 0 even when it fails ? Python, Whisper, ffmpeg
10 juin 2024, par d-bI have a
bashscript that executeswhisperon all sound files in a directory. Whisper usesffmpegto decode sound files to a format it can handle. One of the files in the directory was corrupt and caused ffmpeg to fail. The first time I executed my script it returned1when it hit that file but when I try to reproduce the error it always returns0.

Here is the log from the first run when 1 was returned :


Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 48, in load_audio
 .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/ffmpeg/_run.py", line 325, in run
 raise Error('ffmpeg', out, err)
ffmpeg._run.Error: ffmpeg error (see stderr output for detail)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/bin/whisper", line 8, in <module>
 sys.exit(cli())
 ^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 437, in cli
 result = transcribe(model, audio_path, temperature=temperature, **args)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 121, in transcribe
 mel = log_mel_spectrogram(audio, padding=N_SAMPLES)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 130, in log_mel_spectrogram
 audio = load_audio(audio)
 ^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 51, in load_audio
 raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
RuntimeError: Failed to load audio: ffmpeg version 4.4.4 Copyright (c) 2000-2023 the FFmpeg developers
 built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
 configuration: --prefix=/opt/local --cc=/usr/bin/clang --mandir=/opt/local/share/man --enable-audiotoolbox --disable-indev=jack --disable-libjack --disable-libopencore-amrnb --disable-libopencore-amrwb --disable-libxcb --disable-libxcb-shm --disable-libxcb-xfixes --enable-opencl --disable-outdev=xv --enable-sdl2 --disable-securetransport --enable-videotoolbox --enable-avfilter --enable-avresample --enable-fontconfig --enable-gnutls --enable-libass --enable-libbluray --enable-libdav1d --enable-libfreetype --enable-libfribidi --enable-libmodplug --enable-libmp3lame --enable-libopenjpeg --enable-libopus --enable-librsvg --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libzimg --enable-libzvbi --enable-lzma --enable-pthreads --enable-shared --enable-swscale --enable-zlib --enable-libaom --enable-libsvtav1 --arch=x86_64 --enable-x86asm --enable-gpl --enable-libvidstab --enable-libx264 --enable-libx265 --enable-libxvid --enable-postproc
 libavutil 56. 70.100 / 56. 70.100
 libavcodec 58.134.100 / 58.134.100
 libavformat 58. 76.100 / 58. 76.100
 libavdevice 58. 13.100 / 58. 13.100
 libavfilter 7.110.100 / 7.110.100
 libavresample 4. 0. 0 / 4. 0. 0
 libswscale 5. 9.100 / 5. 9.100
 libswresample 3. 9.100 / 3. 9.100
 libpostproc 55. 9.100 / 55. 9.100
/soundfile1.opus: Invalid data found when processing input


exit: 1 //this is my own output
</module>

and here is an example of when it returns 0 despite the input file is corrupt :


% whisper soundfile1.opus

Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 58, in load_audio
 out = run(cmd, capture_output=True, check=True).stdout
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/opt/local/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/subprocess.py", line 571, in run
 raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ffmpeg', '-nostdin', '-threads', '0', '-i', 'soundfile1.opus', '-f', 's16le', '-ac', '1', '-acodec', 'pcm_s16le', '-ar', '16000', '-']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 597, in cli
 result = transcribe(model, audio_path, temperature=temperature, **args)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 133, in transcribe
 mel = log_mel_spectrogram(audio, model.dims.n_mels, padding=N_SAMPLES)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 140, in log_mel_spectrogram
 audio = load_audio(audio)
 ^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 60, in load_audio
 raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
RuntimeError: Failed to load audio: ffmpeg version 4.4.4 Copyright (c) 2000-2023 the FFmpeg developers
 built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
 configuration: --prefix=/opt/local --cc=/usr/bin/clang --mandir=/opt/local/share/man --enable-audiotoolbox --disable-indev=jack --disable-libjack --disable-libopencore-amrnb --disable-libopencore-amrwb --disable-libxcb --disable-libxcb-shm --disable-libxcb-xfixes --enable-opencl --disable-outdev=xv --enable-sdl2 --disable-securetransport --enable-videotoolbox --enable-avfilter --enable-avresample --enable-fontconfig --enable-gnutls --enable-libass --enable-libbluray --enable-libdav1d --enable-libfreetype --enable-libfribidi --enable-libmodplug --enable-libmp3lame --enable-libopenjpeg --enable-libopus --enable-librsvg --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libzimg --enable-libzvbi --enable-lzma --enable-pthreads --enable-shared --enable-swscale --enable-zlib --enable-libaom --enable-libsvtav1 --arch=x86_64 --enable-x86asm --enable-gpl --enable-libvidstab --enable-libx264 --enable-libx265 --enable-libxvid --enable-postproc
 libavutil 56. 70.100 / 56. 70.100
 libavcodec 58.134.100 / 58.134.100
 libavformat 58. 76.100 / 58. 76.100
 libavdevice 58. 13.100 / 58. 13.100
 libavfilter 7.110.100 / 7.110.100
 libavresample 4. 0. 0 / 4. 0. 0
 libswscale 5. 9.100 / 5. 9.100
 libswresample 3. 9.100 / 3. 9.100
 libpostproc 55. 9.100 / 55. 9.100
soundfile1.opus: Invalid data found when processing input

Skipping soundfile1.opus due to RuntimeError: Failed to load audio: ffmpeg version 4.4.4 Copyright (c) 2000-2023 the FFmpeg developers
 built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
 configuration: --prefix=/opt/local --cc=/usr/bin/clang --mandir=/opt/local/share/man --enable-audiotoolbox --disable-indev=jack --disable-libjack --disable-libopencore-amrnb --disable-libopencore-amrwb --disable-libxcb --disable-libxcb-shm --disable-libxcb-xfixes --enable-opencl --disable-outdev=xv --enable-sdl2 --disable-securetransport --enable-videotoolbox --enable-avfilter --enable-avresample --enable-fontconfig --enable-gnutls --enable-libass --enable-libbluray --enable-libdav1d --enable-libfreetype --enable-libfribidi --enable-libmodplug --enable-libmp3lame --enable-libopenjpeg --enable-libopus --enable-librsvg --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libzimg --enable-libzvbi --enable-lzma --enable-pthreads --enable-shared --enable-swscale --enable-zlib --enable-libaom --enable-libsvtav1 --arch=x86_64 --enable-x86asm --enable-gpl --enable-libvidstab --enable-libx264 --enable-libx265 --enable-libxvid --enable-postproc
 libavutil 56. 70.100 / 56. 70.100
 libavcodec 58.134.100 / 58.134.100
 libavformat 58. 76.100 / 58. 76.100
 libavdevice 58. 13.100 / 58. 13.100
 libavfilter 7.110.100 / 7.110.100
 libavresample 4. 0. 0 / 4. 0. 0
 libswscale 5. 9.100 / 5. 9.100
 libswresample 3. 9.100 / 3. 9.100
 libpostproc 55. 9.100 / 55. 9.100
soundfile1.opus: Invalid data found when processing input

% echo $?
0


When I try to reproduce the behaviour I have both tried to execute the script as well as just running the actual line of code from the command prompt. The actual script looks like this :


if whisper "$file" >> "${directory}/../${transdir}/${name}.txt"; then
 whispersuccess=$?
 echo "exit code $whispersuccess"
else
 whispersuccess=$?
 echo "exit code: $whispersuccess"


I want it to return ¬0 when something like this happens. How do I achieve this ?


-
Why does my script return 0 when it fails ? Bash, Whisper, ffmpeg
30 avril 2024, par d-bI have a
bashscript that executeswhisperon all sound files in a directory. Whisper usesffmpegto decode sound files to a format it can handle. One of the files in the directory was corrupt and caused ffmpeg to fail. The first time I executed my script it returned1when it hit that file but when I try to reproduce the error it always returns0.

Here is the log from the first run when 1 was returned :


Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 48, in load_audio
 .run(cmd=["ffmpeg", "-nostdin"], capture_stdout=True, capture_stderr=True)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/ffmpeg/_run.py", line 325, in run
 raise Error('ffmpeg', out, err)
ffmpeg._run.Error: ffmpeg error (see stderr output for detail)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/bin/whisper", line 8, in <module>
 sys.exit(cli())
 ^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 437, in cli
 result = transcribe(model, audio_path, temperature=temperature, **args)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 121, in transcribe
 mel = log_mel_spectrogram(audio, padding=N_SAMPLES)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 130, in log_mel_spectrogram
 audio = load_audio(audio)
 ^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 51, in load_audio
 raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
RuntimeError: Failed to load audio: ffmpeg version 4.4.4 Copyright (c) 2000-2023 the FFmpeg developers
 built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
 configuration: --prefix=/opt/local --cc=/usr/bin/clang --mandir=/opt/local/share/man --enable-audiotoolbox --disable-indev=jack --disable-libjack --disable-libopencore-amrnb --disable-libopencore-amrwb --disable-libxcb --disable-libxcb-shm --disable-libxcb-xfixes --enable-opencl --disable-outdev=xv --enable-sdl2 --disable-securetransport --enable-videotoolbox --enable-avfilter --enable-avresample --enable-fontconfig --enable-gnutls --enable-libass --enable-libbluray --enable-libdav1d --enable-libfreetype --enable-libfribidi --enable-libmodplug --enable-libmp3lame --enable-libopenjpeg --enable-libopus --enable-librsvg --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libzimg --enable-libzvbi --enable-lzma --enable-pthreads --enable-shared --enable-swscale --enable-zlib --enable-libaom --enable-libsvtav1 --arch=x86_64 --enable-x86asm --enable-gpl --enable-libvidstab --enable-libx264 --enable-libx265 --enable-libxvid --enable-postproc
 libavutil 56. 70.100 / 56. 70.100
 libavcodec 58.134.100 / 58.134.100
 libavformat 58. 76.100 / 58. 76.100
 libavdevice 58. 13.100 / 58. 13.100
 libavfilter 7.110.100 / 7.110.100
 libavresample 4. 0. 0 / 4. 0. 0
 libswscale 5. 9.100 / 5. 9.100
 libswresample 3. 9.100 / 3. 9.100
 libpostproc 55. 9.100 / 55. 9.100
/soundfile1.opus: Invalid data found when processing input


exit: 1 //this is my own output
</module>

and here is an example of when it returns 0 despite the input file is corrupt :


% whisper soundfile1.opus

Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 58, in load_audio
 out = run(cmd, capture_output=True, check=True).stdout
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/opt/local/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/subprocess.py", line 571, in run
 raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ffmpeg', '-nostdin', '-threads', '0', '-i', 'soundfile1.opus', '-f', 's16le', '-ac', '1', '-acodec', 'pcm_s16le', '-ar', '16000', '-']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 597, in cli
 result = transcribe(model, audio_path, temperature=temperature, **args)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/transcribe.py", line 133, in transcribe
 mel = log_mel_spectrogram(audio, model.dims.n_mels, padding=N_SAMPLES)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 140, in log_mel_spectrogram
 audio = load_audio(audio)
 ^^^^^^^^^^^^^^^^^
 File "/Users/db/Library/Python/3.11/lib/python/site-packages/whisper/audio.py", line 60, in load_audio
 raise RuntimeError(f"Failed to load audio: {e.stderr.decode()}") from e
RuntimeError: Failed to load audio: ffmpeg version 4.4.4 Copyright (c) 2000-2023 the FFmpeg developers
 built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
 configuration: --prefix=/opt/local --cc=/usr/bin/clang --mandir=/opt/local/share/man --enable-audiotoolbox --disable-indev=jack --disable-libjack --disable-libopencore-amrnb --disable-libopencore-amrwb --disable-libxcb --disable-libxcb-shm --disable-libxcb-xfixes --enable-opencl --disable-outdev=xv --enable-sdl2 --disable-securetransport --enable-videotoolbox --enable-avfilter --enable-avresample --enable-fontconfig --enable-gnutls --enable-libass --enable-libbluray --enable-libdav1d --enable-libfreetype --enable-libfribidi --enable-libmodplug --enable-libmp3lame --enable-libopenjpeg --enable-libopus --enable-librsvg --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libzimg --enable-libzvbi --enable-lzma --enable-pthreads --enable-shared --enable-swscale --enable-zlib --enable-libaom --enable-libsvtav1 --arch=x86_64 --enable-x86asm --enable-gpl --enable-libvidstab --enable-libx264 --enable-libx265 --enable-libxvid --enable-postproc
 libavutil 56. 70.100 / 56. 70.100
 libavcodec 58.134.100 / 58.134.100
 libavformat 58. 76.100 / 58. 76.100
 libavdevice 58. 13.100 / 58. 13.100
 libavfilter 7.110.100 / 7.110.100
 libavresample 4. 0. 0 / 4. 0. 0
 libswscale 5. 9.100 / 5. 9.100
 libswresample 3. 9.100 / 3. 9.100
 libpostproc 55. 9.100 / 55. 9.100
soundfile1.opus: Invalid data found when processing input

Skipping soundfile1.opus due to RuntimeError: Failed to load audio: ffmpeg version 4.4.4 Copyright (c) 2000-2023 the FFmpeg developers
 built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
 configuration: --prefix=/opt/local --cc=/usr/bin/clang --mandir=/opt/local/share/man --enable-audiotoolbox --disable-indev=jack --disable-libjack --disable-libopencore-amrnb --disable-libopencore-amrwb --disable-libxcb --disable-libxcb-shm --disable-libxcb-xfixes --enable-opencl --disable-outdev=xv --enable-sdl2 --disable-securetransport --enable-videotoolbox --enable-avfilter --enable-avresample --enable-fontconfig --enable-gnutls --enable-libass --enable-libbluray --enable-libdav1d --enable-libfreetype --enable-libfribidi --enable-libmodplug --enable-libmp3lame --enable-libopenjpeg --enable-libopus --enable-librsvg --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libvorbis --enable-libvpx --enable-libzimg --enable-libzvbi --enable-lzma --enable-pthreads --enable-shared --enable-swscale --enable-zlib --enable-libaom --enable-libsvtav1 --arch=x86_64 --enable-x86asm --enable-gpl --enable-libvidstab --enable-libx264 --enable-libx265 --enable-libxvid --enable-postproc
 libavutil 56. 70.100 / 56. 70.100
 libavcodec 58.134.100 / 58.134.100
 libavformat 58. 76.100 / 58. 76.100
 libavdevice 58. 13.100 / 58. 13.100
 libavfilter 7.110.100 / 7.110.100
 libavresample 4. 0. 0 / 4. 0. 0
 libswscale 5. 9.100 / 5. 9.100
 libswresample 3. 9.100 / 3. 9.100
 libpostproc 55. 9.100 / 55. 9.100
soundfile1.opus: Invalid data found when processing input

% echo $?
0


When I try to reproduce the behaviour I have both tried to execute the script as well as just running the actual line of code from the command prompt. The actual script looks like this :


if whisper "$file" >> "${directory}/../${transdir}/${name}.txt"; then
 whispersuccess=$?
 echo "exit code $whispersuccess"
else
 whispersuccess=$?
 echo "exit code: $whispersuccess"


I want it to return ¬0 when something like this happens. How do I achieve this ?


-
ffmpeg failed to load audio file
14 avril 2024, par Vaishnav GhengeFailed to load audio: ffmpeg version 5.1.4-0+deb12u1 Copyright (c) Failed to load audio: ffmpeg version 5.1.4-0+deb12u1 Copyright (c) 2000-2023 the FFmpeg developers
 built with gcc 12 (Debian 12.2.0-14)
 configuration: --prefix=/usr --extra-version=0+deb12u1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librist --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --disable-sndio --enable-libjxl --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-libplacebo --enable-librav1e --enable-shared
 libavutil 57. 28.100 / 57. 28.100
 libavcodec 59. 37.100 / 59. 37.100
 libavformat 59. 27.100 / 59. 27.100
 libavdevice 59. 7.100 / 59. 7.100
 libavfilter 8. 44.100 / 8. 44.100
 libswscale 6. 7.100 / 6. 7.100
 libswresample 4. 7.100 / 4. 7.100
 libpostproc 56. 6.100 / 56. 6.100
/tmp/tmpjlchcpdm.wav: Invalid data found when processing input


backend :



@app.route("/transcribe", methods=["POST"])
def transcribe():
 # Check if audio file is present in the request
 if 'audio_file' not in request.files:
 return jsonify({"error": "No file part"}), 400
 
 audio_file = request.files.get('audio_file')

 # Check if audio_file is sent in files
 if not audio_file:
 return jsonify({"error": "`audio_file` is missing in request.files"}), 400

 # Check if the file is present
 if audio_file.filename == '':
 return jsonify({"error": "No selected file"}), 400

 # Save the file with a unique name
 filename = secure_filename(audio_file.filename)
 unique_filename = os.path.join("uploads", str(uuid.uuid4()) + '_' + filename)
 # audio_file.save(unique_filename)
 
 # Read the contents of the audio file
 contents = audio_file.read()

 max_file_size = 500 * 1024 * 1024
 if len(contents) > max_file_size:
 return jsonify({"error": "File is too large"}), 400

 # Check if the file extension suggests it's a WAV file
 if not filename.lower().endswith('.wav'):
 # Delete the file if it's not a WAV file
 os.remove(unique_filename)
 return jsonify({"error": "Only WAV files are supported"}), 400

 print(f"\033[92m{filename}\033[0m")

 # Call Celery task asynchronously
 result = transcribe_audio.delay(contents)

 return jsonify({
 "task_id": result.id,
 "status": "pending"
 })


@celery_app.task
def transcribe_audio(contents):
 # Transcribe the audio
 try:
 # Create a temporary file to save the audio data
 with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_audio:
 temp_path = temp_audio.name
 temp_audio.write(contents)

 print(f"\033[92mFile temporary path: {temp_path}\033[0m")
 transcribe_start_time = time.time()

 # Transcribe the audio
 transcription = transcribe_with_whisper(temp_path)
 
 transcribe_end_time = time.time()
 print(f"\033[92mTranscripted text: {transcription}\033[0m")

 return transcription, transcribe_end_time - transcribe_start_time

 except Exception as e:
 print(f"\033[92mError: {e}\033[0m")
 return str(e)


frontend :


useEffect(() => {
 const init = () => {
 navigator.mediaDevices.getUserMedia({audio: true})
 .then((audioStream) => {
 const recorder = new MediaRecorder(audioStream);

 recorder.ondataavailable = e => {
 if (e.data.size > 0) {
 setChunks(prevChunks => [...prevChunks, e.data]);
 }
 };

 recorder.onerror = (e) => {
 console.log("error: ", e);
 }

 recorder.onstart = () => {
 console.log("started");
 }

 recorder.start();

 setStream(audioStream);
 setRecorder(recorder);
 });
 }

 init();

 return () => {
 if (recorder && recorder.state === 'recording') {
 recorder.stop();
 }

 if (stream) {
 stream.getTracks().forEach(track => track.stop());
 }
 }
 }, []);

 useEffect(() => {
 // Send chunks of audio data to the backend at regular intervals
 const intervalId = setInterval(() => {
 if (recorder && recorder.state === 'recording') {
 recorder.requestData(); // Trigger data available event
 }
 }, 8000); // Adjust the interval as needed


 return () => {
 if (intervalId) {
 console.log("Interval cleared");
 clearInterval(intervalId);
 }
 };
 }, [recorder]);

 useEffect(() => {
 const processAudio = async () => {
 if (chunks.length > 0) {
 // Send the latest chunk to the server for transcription
 const latestChunk = chunks[chunks.length - 1];

 const audioBlob = new Blob([latestChunk]);
 convertBlobToAudioFile(audioBlob);
 }
 };

 void processAudio();
 }, [chunks]);

 const convertBlobToAudioFile = useCallback((blob: Blob) => {
 // Convert Blob to audio file (e.g., WAV)
 // This conversion may require using a third-party library or service
 // For example, you can use the MediaRecorder API to record audio in WAV format directly
 // Alternatively, you can use a library like recorderjs to perform the conversion
 // Here's a simplified example using recorderjs:

 const reader = new FileReader();
 reader.onload = () => {
 const audioBuffer = reader.result; // ArrayBuffer containing audio data

 // Send audioBuffer to Flask server or perform further processing
 sendAudioToFlask(audioBuffer as ArrayBuffer);
 };

 reader.readAsArrayBuffer(blob);
 }, []);

 const sendAudioToFlask = useCallback((audioBuffer: ArrayBuffer) => {
 const formData = new FormData();
 formData.append('audio_file', new Blob([audioBuffer]), `speech_audio.wav`);

 console.log(formData.get("audio_file"));

 fetch('http://34.87.75.138:8000/transcribe', {
 method: 'POST',
 body: formData
 })
 .then(response => response.json())
 .then((data: { task_id: string, status: string }) => {
 pendingTaskIdsRef.current.push(data.task_id);
 })
 .catch(error => {
 console.error('Error sending audio to Flask server:', error);
 });
 }, []);


I was trying to pass the audio from frontend to whisper model which is in flask app


Syndiquer tout le site
