Back to browse
GitHub Repository

Snap any video URL or audio file into plaintext. No GPU. No cloud. One command.

267 starsPython

CPU transcription for YouTube/TikTok/X, now 3x faster and diarization

by mrkn1·May 27, 2026·3 points·0 comments

AI Analysis

●●SolidCozySolve My Problem

CPU-only ONNX transcription when Whisper.cpp already handles this well.

Strengths
  • Streaming Zipformer transducer runs several times realtime on laptop CPU
  • Lean dependency stack: sherpa-onnx, numpy, yt-dlp — no PyTorch
  • Diarization and timestamps work offline after initial 80 MB model download
Weaknesses
  • Local CPU transcription already solved by Whisper.cpp and faster-whisper
  • No novel architecture — wraps existing ONNX models with yt-dlp fetching
Category
Target Audience

Developers and content creators needing offline transcription

Similar To

Whisper.cpp · faster-whisper · AssemblyAI

Similar Projects

AI/ML●●●Banger

Diarize – CPU-only speaker diarization, 7x faster than pyannote

Matches pyannote on accuracy, runs 8x faster on CPU, no signup—genuine infrastructure win.

Solve My ProblemDark Horse
loookas
343mo ago
AI/ML●●Solid

Podscript – Podcast/YouTube Transcription CLI

Outputs ready-to-use Markdown with speaker diarization and timestamps, accepts Apple Podcasts/YouTube/RSS links, and can run fully locally or use ElevenLabs for higher-quality diarization. Not groundbreaking — speech-to-text pipelines already exist — but the one-command UX, RSS browsing/search flags, and explicit local-mode make it genuinely useful for folks who want tidy transcripts without wiring together multiple tools.

Solve My ProblemNiche Gem
timf34
103mo ago
SaaS●●Solid

Transcriptum – fast video transcription with speaker labels and summary

It pairs WhisperX-grade transcription (speaker diarization and word-level timestamps) with optional multi-LLM analysis — summaries, Q&A, sentiment, topics and even fact-checking — plus YouTube import and standard export formats. Being vendor-agnostic and offering fact-checking is a smart differentiator, but the space is crowded (Descript/Otter/etc.); clearer accuracy numbers, pricing, or unique workflow hooks would make this stand out.

Solve My ProblemSlick
lpeancovschi
103mo ago