Whisper is an autoregressive language model developed by OpenAI. It is trained on a large corpus of text using a transformer architecture and is capable of generating high-quality natural language text. Whisper can be used for tasks such as language modeling, text completion, and text generation. It has shown impressive performance on various benchmarks and has been released by OpenAI to encourage research in the field of language modeling. Whisper is not yet available for public use, but it has the potential to transform the field of natural language processing and generate new opportunities for language-based applications.
Local web app for transcription and translation services for audio and video using Whisper models
A bot that downloads, transcribes and analyzes calls to find insights for sales advisors
Telegram bot powered by Ollama, capable of handling text and voice messages, with configurable language models and system prompts
Code and example data for the paper: Rule Based Rewards for Language Model Safety
This repository contains code for fine-tuning the Whisper speech-to-text model
A real-time speech-to-text transcriber using the Whisper model, designed for efficiency and ease of use in the console