torch-harmonics

by NVIDIA

Spherical signal transforms — used in advanced ASR research.

TL;DR

Spherical signal transforms — used in advanced ASR research.

Best for research workloads adapting spherical transforms to speech. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux

What it is

NVIDIA's library for differentiable spherical harmonics. BSD-3-Clause.

Best for: Research workloads adapting spherical transforms to speech.
Watch out for: Niche; not an ASR engine.

Install / use

pip install torch-harmonics

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

torch-harmonics vs Whipscribe

Featuretorch-harmonicsWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages199
PlatformsLinuxWeb, API, MCP

Alternatives to torch-harmonics

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.