# kadirnar/whisper-plus

WhisperPlus: Faster, Smarter, and More Capable 🚀

Repository: https://github.com/kadirnar/whisper-plus
Canonical: https://ross.abutalabs.com/products/whisper-plus
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-03T20:59:14+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 8, longevity 72
- inputs: {"age_days": 1016, "days_push": 30, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1956, forks 147 (observed 2026-08-28T04:05:59.051231+00:00)

## What it is
A Python library wrapping OpenAI Whisper-family models (including distil-whisper and MLX variants) for fast speech-to-text transcription with quantization and flash-attention support. It also provides YouTube audio download utilities and a speaker diarization pipeline.

## Use cases
- transcribe youtube videos to text
- convert audio to text with whisper
- run whisper faster with quantization
- transcribe audio on apple silicon with mlx
- download youtube audio for transcription
- batch transcribe long audio files

## When to choose
- you want a high-level pipeline over Whisper models with quantization and flash attention
- you need to transcribe YouTube videos end-to-end in Python
- you run on Apple Silicon and want MLX-accelerated Whisper

## When to avoid
- you need a production-grade managed transcription service
- you only need simple audio playback or editing rather than transcription
- you require non-Whisper ASR models

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, audio-processing, machine-learning, llm-inference
- domain: speech-processing, machine-learning
- platform: python, cli
- tags: whisper, transcription, youtube-downloader, quantization, mlx, huggingface, distil-whisper, audio, natural-language-processing, macos, gpu

## Member repositories
- kadirnar/whisper-plus (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:59.051231+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:06:13.902587+00:00, confidence not recorded.
  - readme: https://github.com/kadirnar/whisper-plus (fetched 2026-08-28T04:05:59.051231+00:00, sha 5343a79ea8c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.