Skip to content

Instantly share code, notes, and snippets.

@int128

int128/README.md

Last active March 31, 2025 23:39
Show Gist options
  • Save int128/e7d6a93fd9e3ca18043dc901cc7f67d1 to your computer and use it in GitHub Desktop.
Save int128/e7d6a93fd9e3ca18043dc901cc7f67d1 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. int128 revised this gist Mar 31, 2025. 2 changed files with 25 additions and 0 deletions.
    7 changes: 7 additions & 0 deletions README.md
    View file
    Original file line number Diff line number Diff line change
    @@ -21,3 +21,10 @@ Run the example script of https://github.com/SYSTRAN/faster-whisper?tab=readme-o
    ```sh
    python3 test.py
    ```

    Here is an example log of time to transcript 30 minutes audio.

    ```
    2025-03-30 06:21:31.513916
    2025-03-30 06:23:53.890056
    ```
    18 changes: 18 additions & 0 deletions example.py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,18 @@
    from datetime import datetime
    from faster_whisper import WhisperModel

    print(datetime.now())

    model_size = "large-v3"

    # Run on GPU with FP16
    model = WhisperModel(model_size, device="cuda", compute_type="float16")

    segments, info = model.transcribe("audio.mp3", beam_size=5)

    print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

    for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

    print(datetime.now())
  2. int128 created this gist Mar 30, 2025.
    23 changes: 23 additions & 0 deletions README.md
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,23 @@
    Spin up an instance of g4dn.xlarge with Deep Learning Base OSS Nvidia Driver GPU AMI (Amazon Linux 2023).
    Log in to the instance via Session Manager.

    Make sure the GPU is available.

    ```sh
    nvidia-smi
    ```

    Install https://github.com/SYSTRAN/faster-whisper and cuDNN.

    ```sh
    pip3 install faster-whisper

    pip3 install nvidia-cublas-cu12 'nvidia-cudnn-cu12==9.*'
    export LD_LIBRARY_PATH=`python3 -c 'import os; import nvidia.cublas.lib; import nvidia.cudnn.lib; print(os.path.dirname(nvidia.cublas.lib.__file__) + ":" + os.path.dirname(nvidia.cudnn.lib.__file__))'`
    ```

    Run the example script of https://github.com/SYSTRAN/faster-whisper?tab=readme-ov-file#faster-whisper.

    ```sh
    python3 test.py
    ```