Home/Speech & Audio/TheWhisper

TheWhisper

TheStageAI/TheWhisper

Optimized Whisper models for streaming and on-device use

GitHub Website

GraphCanon updated 3w · GitHub synced 3w

894 stars55 forksLast push 2mo Python MIT

Decision brief

TheWhisper optimizes Whisper models for streaming and on-device use, supporting various platforms like Apple Silicon, Nvidia GPUs, with real-time capabilities.

Good fit when

Optimized for streaming speech recognition on platforms like Apple Silicon and Nvidia GPUs.
When you need specific real-time performance and word timestamps on supported hardware.

Avoid when

Avoid if your project requires compatibility with Intel CPUs as it's optimized for Apple and Nvidia.
Not suitable without a GPU or specific hardware that meets the 2.5 GB RAM minimum (Nvidia) or 2 GB (Apple).

Observed Jul 12, 2026 · Source: enrich:decision_facts

TheWhisper alternatives Trust report

TheWhisper vs whisper.cpp

Verify the decision

Maintenance and security

Full trust report

Maintenance: Steady (45d since push); As of 3w
Provenance: Not a fork · Organization account; As of 3w
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install TheWhisper

PyPI

How it fits your stack(1)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Alternative

whisper.cpp

TheWhisper is another optimized version of the Whisper model, similar to whisper.cpp, but focused on streaming and on-device use cases.

alternative

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

whisper-diarization5.6k★

AlternativeRelated

whisper-diarization5.6k★

openwhispr5.0k★

AlternativeRelated

Similar tools

Same-category neighbours not already linked as typed edges.

faster-whisper

Faster Whisper transcription with CTranslate2

25k★

whisperX

WhisperX for automatic speech recognition with word-level timestamps and diarization

23k★

FunASR

Industrial-grade speech recognition toolkit

20k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

TheStageAI/TheWhisper repository provides optimized Whisper models tailored for speech recognition, transcription, and translation tasks. It supports various platforms including Apple Silicon and Nvidia GPUs with detailed setup instructions.

Capability facts

Languages: python
Source: github.language+pyproject.toml · Jul 31, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 31, 2026)

- **Python version**: 3.10-3.12

Source link

README

Install for Apple

pip install .[apple]

Install for Nvidia

pip install .[nvidia]

Install for Nvidia with TheStage AI optmized engines

pip install 'thestage-elastic-models[nvidia]==0.1.7' --index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-production/simple --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.org/simple
pip install .[nvidia]
pip install thestage

Install for Jetson-Thor with TheStage AI optmized engines

Make sure you have tensorrt==10.13.3.9 installed on your jetson and run:

pip install thestage-elastic-models[thor]==0.1.7 --extra-index-url https://thestage.jfrog.io/artifactory/api/pypi/pypi-thestage-ai-jetson-thor/simple -i https://pypi.jetson-ai-lab.io/sbsa/cu130/+simple/ --extra-index-url https://pypi.org
pip install .
pip install thestage

Then generate access token on TheStage AI Platform in your profile and execute the following command:

thestage config set -t <YOUR_API_TOKEN>

🏗️ Support Matrix and System Requirements

Feature	whisper-large-v3 (Nvidia)	whisper-large-v3 (Apple)	whisper-large-v3-turbo (Nvidia)	whisper-large-v3-turbo (Apple)
Streaming	✅	✅	✅	✅
Accelerated	✅	✅	✅	✅
Word Timestamps	✅	✅	✅	✅
Multilingual	✅	✅	✅	✅
10s Chunk Mode	✅	✅	✅	✅
15s Chunk Mode	✅	✅	✅	✅
20s Chunk Mode	✅	✅	✅	✅
30s Chunk Mode	✅	✅	✅	✅

Nvidia GPU Requirements

Supported GPUs: RTX 4090, RTX 5090, L40s, H100, A100, Jetson-Thor
Operating System: Ubuntu 20.04+
Minimum RAM: 2.5 GB (5 GB recommended for large-v3 model)
CUDA Version: 11.8 or higher
Driver Version: 520.0 or higher
Python version: 3.10-3.12

Apple Silicon Requirements

Supported Chipsets: M1, M1 Pro, M1 Max, M1 Ultra, M2, M2 Pro, M2 Max, M2 Ultra, M3, M3 Pro, M3 Max, M4, M4 Pro, M4 Max
Operating System: macOS 15.0 (Ventura) or later, iOS 18.0 or later
Minimum RAM: 2 GB (4 GB recommended for large-v3 model)
Python version: 3.10-3.12

🏢 Enterprise License Summary

To get commercial license for bigger number of GPUs to use TheStage AI optimized engines please contact us here: Service request

Platform	Engine Type	Status	License
NVIDIA GPUs (CUDA)	Pytorch HF Transformers	✅ Stable	Free
macOS / Apple Silicon	CoreML Engine + MLX	✅ Stable	Free
NVIDIA GPUs (CUDA)	TheStage AI (Optimized)	✅ Stable	Free ≤ 4 GPUs/year for small orgs

For agents

This page has a .md twin and JSON over the API.

/tools/thestageai-thewhisper.md GET /api/graphcanon/tools/thestageai-thewhisper GET /api/graphcanon/graph?tool=thestageai-thewhisper