An opinionated CLI to transcribe Audio files w/ Whisper on-device
Insanely Fast Whisper is a high-performance command-line tool designed to dramatically accelerate speech-to-text transcription using OpenAI’s Whisper models on local hardware. It leverages modern optimizations such as batch processing, mixed precision, and advanced attention mechanisms like Flash Attention to significantly reduce inference time while maintaining high transcription accuracy. The project is built on top of the Transformers ecosystem and integrates with libraries such as...
...The code has been developed in Python 2.7
The following packages are required to be installed before running the program.
import speech
import sys
import time
import textblob
Links:
https://pypi.python.org/pypi/speech/0.5.2
http://textblob.readthedocs.org/en/dev/
Please contribute to this project to lead to a more refined and useful open source software.