I’m happy to announce that TurboScribe’s free tier is expanding! Starting today, TurboScribe’s free tier now includes Whale mode, powered by Whisper large-v2. Previously, usage of Whale was limited to TurboScribe Unlimited members. This new expansion of the free tier means you can now try it out for free. Whale is our highest accuracy mode.
Overview This is a new major release adding integer quantization and partial GPU (NVIDIA) support Integer quantization This allows the ggml Whisper models to be converted from the default 16-bit floating point weights to 4, 5 or 8 bit integer weights. The resulting quantized models are smaller in disk size and memory usage and can

This repository contains optimised JAX code for OpenAI’s Whisper Model, largely built on the 🤗 Hugging Face Transformers Whisper implementation. Compared to OpenAI’s PyTorch code, Whisper JAX runs over 70x faster, making it the fastest Whisper implementation available. The JAX code is compatible on CPU, GPU and TPU, and can be run standalone (see Pipeline

Whisper CLI is a command-line interface for transcribing and translating audio using OpenAI’s Whisper API. It also allows you to manage multiple OpenAI API keys as separate environments. To install Whisper CLI, simply run: Setup To get started with Whisper CLI, you’ll need to set your OpenAI API key. You can do this using the

We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using twitter.com. You can see a list of supported browsers in our Help Center. Help Center