Recherche avancée

Sur d’autres sites (4775)

• FFmpeg fails to draw text

  6 avril 2024, par Edoardo Balducci

  I've rarely used ffmpeg before, so, sorry If the question is too dumb.
I have a problem adding a text layer to a video frame using ffmpeg.

  


  This is my current code :

  


  import subprocess
from PyQt5.QtGui import QPixmap, QImage
from PyQt5.QtWidgets import QLabel

class VideoThumbnailLabel(QLabel):
    def __init__(self, file_path, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.video = video
        video_duration = self.get_video_duration(file_path)
        thumbnail_path = self.get_thumbnail(file_path, video_duration)
        if thumbnail_path:
            self.setPixmap(QPixmap(thumbnail_path).scaled(160, 90, Qt.KeepAspectRatio))
        self.setToolTip(f"{video.title}\n{video.description}")

    def get_video_duration(self, video_path):
        """Returns the duration of the video in seconds."""
        command = [
            'ffprobe', '-v', 'error', '-show_entries',
            'format=duration', '-of',
            'default=noprint_wrappers=1:nokey=1', video_path
        ]
        try:
            result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
            if result.returncode != 0:
                print(f"ffprobe error: {result.stderr}")
                return 0
            duration = float(result.stdout)
            return int(duration)  # Returning duration as an integer for simplicity
        except Exception as e:
            print(f"Error getting video duration: {e}")
            return 0

    def get_thumbnail(self, video_path, duration):
        """Generates a thumbnail with the video duration overlaid."""
        output_path = "thumbnail.jpg"  # Temporary thumbnail file
        duration_str = f"{duration // 3600:02d}:{(duration % 3600) // 60:02d}:{duration % 60:02d}"
        command = [
            'ffmpeg', '-i', video_path,
            '-ss', '00:00:01',  # Time to take the screenshot
            '-frames:v', '1',  # Number of frames to capture
            '-vf', f"drawtext=text='Duration: {duration_str}':x=10:y=10:fontsize=24:fontcolor=white",
            '-q:v', '2',  # Output quality
            '-y',  # Overwrite output files without asking
            output_path
        ]
        try:
            result = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
            if result.returncode != 0:
                print(f"ffmpeg error: {result.stderr}")
                return None
            return output_path
        except Exception as e:
            print(f"Error generating thumbnail with duration: {e}")
            return None


  


  and it is used like this :

  


  for i, video in enumerate(self.videos):
    video_widget = VideoThumbnailLabel(video.file)
    video_widget.mousePressEvent = lambda event, v=video: self.onThumbnailClick(
        v
    )
    self.layout.addWidget(video_widget, i // 3, i % 3)


  


  I'm facing a problem where I am not able to get the thumbnail if I try to add the duration (I've tested it without the draw filter and worked fine)

  


  I get this error (from the result.returncode) that I'm not able to comprehend :

  


  ffmpeg error: b"ffmpeg version 6.1.1 Copyright (c) 2000-2023 the FFmpeg developers\n  built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)\n  configuration: --prefix=/opt/homebrew/Cellar/ffmpeg/6.1.1_4 --enable-shared --enable-pthreads --enable-version3 --cc=clang --host-cflags= --host-ldflags='-Wl,-ld_classic' --enable-ffplay --enable-gnutls --enable-gpl --enable-libaom --enable-libaribb24 --enable-libbluray --enable-libdav1d --enable-libharfbuzz --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librav1e --enable-librist --enable-librubberband --enable-libsnappy --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtesseract --enable-libtheora --enable-libvidstab --enable-libvmaf --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libxvid --enable-lzma --enable-libfontconfig --enable-libfreetype --enable-frei0r --enable-libass --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopenvino --enable-libspeex --enable-libsoxr --enable-libzmq --enable-libzimg --disable-libjack --disable-indev=jack --enable-videotoolbox --enable-audiotoolbox --enable-neon\n  libavutil      58. 29.100 / 58. 29.100\n  libavcodec     60. 31.102 / 60. 31.102\n  libavformat    60. 16.100 / 60. 16.100\n  libavdevice    60.  3.100 / 60.  3.100\n  libavfilter     9. 12.100 /  9. 12.100\n  libswscale      7.  5.100 /  7.  5.100\n  libswresample   4. 12.100 /  4. 12.100\n  libpostproc    57.  3.100 / 57.  3.100\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from '/Users/edoardo/Projects/work/test/BigBuckBunny.mp4':\n  Metadata:\n    major_brand     : mp42\n    minor_version   : 0\n    compatible_brands: isomavc1mp42\n    creation_time   : 2010-01-10T08:29:06.000000Z\n  Duration: 00:09:56.47, start: 0.000000, bitrate: 2119 kb/s\n  Stream #0:0[0x1](und): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 125 kb/s (default)\n    Metadata:\n      creation_time   : 2010-01-10T08:29:06.000000Z\n      handler_name    : (C) 2007 Google Inc. v08.13.2007.\n      vendor_id       : [0][0][0][0]\n  Stream #0:1[0x2](und): Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 1280x720 [SAR 1:1 DAR 16:9], 1991 kb/s, 24 fps, 24 tbr, 24k tbn (default)\n    Metadata:\n      creation_time   : 2010-01-10T08:29:06.000000Z\n      handler_name    : (C) 2007 Google Inc. v08.13.2007.\n      vendor_id       : [0][0][0][0]\n[Parsed_drawtext_0 @ 0x60000331cd10] Both text and text file provided. Please provide only one\n[AVFilterGraph @ 0x600002018000] Error initializing filters\n[vost#0:0/mjpeg @ 0x13ce0c7e0] Error initializing a simple filtergraph\nError opening output file thumbnail.jpg.\nError opening output files: Invalid argument\n"


  


  I've installed both ffmpeg and ffmprobe in my machine :

  


  ┌(edoardomacbook-air)-[~/Projects/work/tests-scripts]                                                                                                                                   
└─ $ ffmpeg -version && ffprobe -version                                                                                                                                                              2 ⚙ 
ffmpeg version 6.1.1 Copyright (c) 2000-2023 the FFmpeg developers
built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
configuration: --prefix=/opt/homebrew/Cellar/ffmpeg/6.1.1_4 --enable-shared --enable-pthreads --enable-version3 --cc=clang --host-cflags= --host-ldflags='-Wl,-ld_classic' --enable-ffplay --enable-gnutls --enable-gpl --enable-libaom --enable-libaribb24 --enable-libbluray --enable-libdav1d --enable-libharfbuzz --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librav1e --enable-librist --enable-librubberband --enable-libsnappy --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtesseract --enable-libtheora --enable-libvidstab --enable-libvmaf --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libxvid --enable-lzma --enable-libfontconfig --enable-libfreetype --enable-frei0r --enable-libass --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopenvino --enable-libspeex --enable-libsoxr --enable-libzmq --enable-libzimg --disable-libjack --disable-indev=jack --enable-videotoolbox --enable-audiotoolbox --enable-neon
libavutil      58. 29.100 / 58. 29.100
libavcodec     60. 31.102 / 60. 31.102
libavformat    60. 16.100 / 60. 16.100
libavdevice    60.  3.100 / 60.  3.100
libavfilter     9. 12.100 /  9. 12.100
libswscale      7.  5.100 /  7.  5.100
libswresample   4. 12.100 /  4. 12.100
libpostproc    57.  3.100 / 57.  3.100
ffprobe version 6.1.1 Copyright (c) 2007-2023 the FFmpeg developers
built with Apple clang version 15.0.0 (clang-1500.1.0.2.5)
configuration: --prefix=/opt/homebrew/Cellar/ffmpeg/6.1.1_4 --enable-shared --enable-pthreads --enable-version3 --cc=clang --host-cflags= --host-ldflags='-Wl,-ld_classic' --enable-ffplay --enable-gnutls --enable-gpl --enable-libaom --enable-libaribb24 --enable-libbluray --enable-libdav1d --enable-libharfbuzz --enable-libjxl --enable-libmp3lame --enable-libopus --enable-librav1e --enable-librist --enable-librubberband --enable-libsnappy --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtesseract --enable-libtheora --enable-libvidstab --enable-libvmaf --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libxvid --enable-lzma --enable-libfontconfig --enable-libfreetype --enable-frei0r --enable-libass --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopenvino --enable-libspeex --enable-libsoxr --enable-libzmq --enable-libzimg --disable-libjack --disable-indev=jack --enable-videotoolbox --enable-audiotoolbox --enable-neon
libavutil      58. 29.100 / 58. 29.100
libavcodec     60. 31.102 / 60. 31.102
libavformat    60. 16.100 / 60. 16.100
libavdevice    60.  3.100 / 60.  3.100
libavfilter     9. 12.100 /  9. 12.100
libswscale      7.  5.100 /  7.  5.100
libswresample   4. 12.100 /  4. 12.100
libpostproc    57.  3.100 / 57.  3.100


  


  Does anyone see the problem ?

  


  ---

  


  P.S. : I know that I havent provided a minimal reproducible example, but since I don't know where the problem lies I didn't want to exclude anything

  


• FFmpeg RTSP drop rate increases when frame rate is reduced

  13 avril 2024, par Avishka Perera

  I need to read an RTSP stream, process the images individually in Python, and then write the images back to an RTSP stream. As the RTSP server, I am using Mediamtx [1]. For streaming, I am using FFmpeg [2].

  


  I have the following code that works perfectly fine. For simplification purposes, I am streaming three generated images.

  


  import time
import numpy as np
import subprocess

width, height = 640, 480
fps = 25
rtsp_server_address = f"rtsp://localhost:8554/mystream"

ffmpeg_cmd = [
    "ffmpeg",
    "-re",
    "-f",
    "rawvideo",
    "-pix_fmt",
    "rgb24",
    "-s",
    f"{width}x{height}",
    "-i",
    "-",
    "-r",
    str(fps),
    "-avoid_negative_ts",
    "make_zero",
    "-vcodec",
    "libx264",
    "-threads",
    "4",
    "-f",
    "rtsp",
    rtsp_server_address,
]
colors = np.array(
    [
        [255, 0, 0],
        [0, 255, 0],
        [0, 0, 255],
    ]
).reshape(3, 1, 1, 3)
images = (np.ones((3, width, height, 3)) * colors).astype(np.uint8)

if __name__ == "__main__":

    process = subprocess.Popen(ffmpeg_cmd, stdin=subprocess.PIPE)
    start = time.time()
    exported = 0
    while True:
        exported += 1
        next_time = start + exported / fps
        now = time.time()
        if next_time > now:
            sleep_dur = next_time - now
            time.sleep(sleep_dur)

        image = images[exported % 3]
        image_bytes = image.tobytes()

        process.stdin.write(image_bytes)
        process.stdin.flush()

    process.stdin.close()
    process.wait()


  


  The issue is, that I need to run this at 10 fps because the processing step is heavy and can only afford 10 fps. Hence, as I reduce the frame rate from 25 to 10, the drop rate increases from 0% to 100%. And after a few iterations, I get a BrokenPipeError: [Errno 32] Broken pipe. Refer to the appendix for the complete log.

  


  As an alternative, I can use OpenCV compiled from source with GStreamer [3], but I prefer using FFmpeg to make the shipping process simple. Since compiling OpenCV from source can be tedious and dependent on the system.

  


  References

  


  [1] Mediamtx (formerly rtsp-simple-server) : https://github.com/bluenviron/mediamtx

  


  [2] FFmpeg : https://github.com/FFmpeg/FFmpeg

  


  [3] Compile OpenCV with GStreamer : https://github.com/bluenviron/mediamtx?tab=readme-ov-file#opencv

  


  Appendix

  


  Creating the source stream

  


  To instantiate the unprocessed stream, I use the following command. This streams the content of my webcam as and RTSP stream.

  


  ffmpeg -video_size 1280x720 -i /dev/video0  -avoid_negative_ts make_zero -vcodec libx264 -r 10 -f rtsp rtsp://localhost:8554/webcam


  


  Error log

  


  ffmpeg version 6.1.1 Copyright (c) 2000-2023 the FFmpeg developers&#xA;  built with gcc 12.3.0 (conda-forge gcc 12.3.0-5)&#xA;  configuration: --prefix=/home/conda/feedstock_root/build_artifacts/ffmpeg_1712656518955/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_plac --cc=/home/conda/feedstock_root/build_artifacts/ffmpeg_1712656518955/_build_env/bin/x86_64-conda-linux-gnu-cc --cxx=/home/conda/feedstock_root/build_artifacts/ffmpeg_1712656518955/_build_env/bin/x86_64-conda-linux-gnu-c&#x2B;&#x2B; --nm=/home/conda/feedstock_root/build_artifacts/ffmpeg_1712656518955/_build_env/bin/x86_64-conda-linux-gnu-nm --ar=/home/conda/feedstock_root/build_artifacts/ffmpeg_1712656518955/_build_env/bin/x86_64-conda-linux-gnu-ar --disable-doc --disable-openssl --enable-demuxer=dash --enable-hardcoded-tables --enable-libfreetype --enable-libharfbuzz --enable-libfontconfig --enable-libopenh264 --enable-libdav1d --enable-gnutls --enable-libmp3lame --enable-libvpx --enable-libass --enable-pthreads --enable-vaapi --enable-libopenvino --enable-gpl --enable-libx264 --enable-libx265 --enable-libaom --enable-libsvtav1 --enable-libxml2 --enable-pic --enable-shared --disable-static --enable-version3 --enable-zlib --enable-libopus --pkg-config=/home/conda/feedstock_root/build_artifacts/ffmpeg_1712656518955/_build_env/bin/pkg-config&#xA;  libavutil      58. 29.100 / 58. 29.100&#xA;  libavcodec     60. 31.102 / 60. 31.102&#xA;  libavformat    60. 16.100 / 60. 16.100&#xA;  libavdevice    60.  3.100 / 60.  3.100&#xA;  libavfilter     9. 12.100 /  9. 12.100&#xA;  libswscale      7.  5.100 /  7.  5.100&#xA;  libswresample   4. 12.100 /  4. 12.100&#xA;  libpostproc    57.  3.100 / 57.  3.100&#xA;Input #0, rawvideo, from &#x27;fd:&#x27;:&#xA;  Duration: N/A, start: 0.000000, bitrate: 184320 kb/s&#xA;  Stream #0:0: Video: rawvideo (RGB[24] / 0x18424752), rgb24, 640x480, 184320 kb/s, 25 tbr, 25 tbn&#xA;Stream mapping:&#xA;  Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))&#xA;[libx264 @ 0x5e2ef8b01340] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2&#xA;[libx264 @ 0x5e2ef8b01340] profile High 4:4:4 Predictive, level 2.2, 4:4:4, 8-bit&#xA;[libx264 @ 0x5e2ef8b01340] 264 - core 164 r3095 baee400 - H.264/MPEG-4 AVC codec - Copyleft 2003-2022 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=4 threads=4 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=10 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00&#xA;Output #0, rtsp, to &#x27;rtsp://localhost:8554/mystream&#x27;:&#xA;  Metadata:&#xA;    encoder         : Lavf60.16.100&#xA;  Stream #0:0: Video: h264, yuv444p(tv, progressive), 640x480, q=2-31, 10 fps, 90k tbn&#xA;    Metadata:&#xA;      encoder         : Lavc60.31.102 libx264&#xA;    Side data:&#xA;      cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A&#xA;[vost#0:0/libx264 @ 0x5e2ef8b01080] Error submitting a packet to the muxer: Broken pipe   &#xA;[out#0/rtsp @ 0x5e2ef8afd780] Error muxing a packet&#xA;[out#0/rtsp @ 0x5e2ef8afd780] video:1kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown&#xA;frame=    1 fps=0.1 q=-1.0 Lsize=N/A time=00:00:04.70 bitrate=N/A dup=0 drop=70 speed=0.389x    &#xA;[libx264 @ 0x5e2ef8b01340] frame I:16    Avg QP: 6.00  size:   147&#xA;[libx264 @ 0x5e2ef8b01340] frame P:17    Avg QP: 9.94  size:   101&#xA;[libx264 @ 0x5e2ef8b01340] frame B:17    Avg QP: 9.94  size:    64&#xA;[libx264 @ 0x5e2ef8b01340] consecutive B-frames: 50.0%  0.0% 42.0%  8.0%&#xA;[libx264 @ 0x5e2ef8b01340] mb I  I16..4: 81.3% 18.7%  0.0%&#xA;[libx264 @ 0x5e2ef8b01340] mb P  I16..4: 52.9%  0.0%  0.0%  P16..4:  0.0%  0.0%  0.0%  0.0%  0.0%    skip:47.1%&#xA;[libx264 @ 0x5e2ef8b01340] mb B  I16..4:  0.0%  5.9%  0.0%  B16..8:  0.1%  0.0%  0.0%  direct: 0.0%  skip:94.0%  L0:56.2% L1:43.8% BI: 0.0%&#xA;[libx264 @ 0x5e2ef8b01340] 8x8 transform intra:15.4% inter:100.0%&#xA;[libx264 @ 0x5e2ef8b01340] coded y,u,v intra: 0.0% 0.0% 0.0% inter: 0.0% 0.0% 0.0%&#xA;[libx264 @ 0x5e2ef8b01340] i16 v,h,dc,p: 97%  0%  3%  0%&#xA;[libx264 @ 0x5e2ef8b01340] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu:  0%  0% 100%  0%  0%  0%  0%  0%  0%&#xA;[libx264 @ 0x5e2ef8b01340] Weighted P-Frames: Y:52.9% UV:52.9%&#xA;[libx264 @ 0x5e2ef8b01340] ref P L0: 88.9%  0.0%  0.0% 11.1%&#xA;[libx264 @ 0x5e2ef8b01340] kb/s:8.27&#xA;Conversion failed!&#xA;Traceback (most recent call last):&#xA;  File "/home/avishka/projects/read-process-stream/minimal-ffmpeg-error.py", line 58, in <module>&#xA;    process.stdin.write(image_bytes)&#xA;BrokenPipeError: [Errno 32] Broken pipe&#xA;</module>

  


• ffmpeg failed to load audio file

  14 avril 2024, par Vaishnav Ghenge

  Failed 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