Whisper JAX

JAX-based Whisper implementation optimized for TPU/GPU with 70x+ speedup.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

Whisper JAX is a JAX and Flax implementation of OpenAI Whisper, built on the Hugging Face Transformers version and optimized for TPU and GPU, reporting over 70 times faster inference than the original PyTorch code on TPU. It supports batched inference and chunked processing for long audio and runs on CPU, GPU, or TPU standalone or as an endpoint. Released under the Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
License
Apache-2.0
Minimum VRAM
8 GB
Added
Apr 3, 2026

Related Tools

CLI tool that transcribes audio 10x faster using pipeline optimizations.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)

Self-supervised speech representation model by Meta for ASR.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)
Featured

High-performance C/C++ port of Whisper for CPU-based speech recognition.

Open SourceSelf HostedOffline
Easy
0.0 (0)

Non-autoregressive ASR model by Alibaba achieving fast parallel transcription.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)
Featured

General-purpose speech recognition model by OpenAI trained on 680K hours of multilingual audio.

Open SourceSelf HostedOffline
Easy
0.0 (0)

Multilingual ASR model by NVIDIA supporting 4 languages with translation.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Browse all Speech-to-Text / Speech Recognition tools