mlx-examples/whisper
Awni Hannun 54952a0d80
Merge pull request #12 from chatgpt-1/main
Fix: timestamp extraction bug in transcribe function
2023-12-07 08:53:30 -08:00
..
whisper Fix timestamp extraction bug in transcribe function 2023-12-06 20:34:30 +08:00
benchmark.py Benchmark all models if user allows. 2023-12-07 00:07:42 +05:30
README.md a few examples 2023-11-29 08:17:26 -08:00
requirements.txt a few examples 2023-11-29 08:17:26 -08:00
test.py add copyright in source 2023-11-30 11:08:53 -08:00

whisper

Whisper in MLX.

First install the dependencies:

(TODO, MLX install link / command / add to requirements.txt)

pip install -r requirements.txt

Install ffmpeg:

# on MacOS using Homebrew (https://brew.sh/)
brew install ffmpeg

Then transcribe audio with:

import whisper

text = whisper.transcribe(speech_file)["text"]