Whisper Small Alternatives

Whisper Tiny is an open-source automatic speech recognition (ASR) model developed by OpenAI. It enables developers to transcribe audio files into text across multiple languages, optimized for lightweight and efficient inference. The model is suitable for integration into speech-to-text pipelines and offline transcription tools.

This is a converted version of OpenAI's Whisper-small model exported to ONNX format for use with Transformers.js and other ONNX runtimes. It performs automatic speech recognition, converting spoken audio into text in multiple languages. The model is designed for integration into web applications and environments where native PyTorch is not suitable.

Whisper Large v3 is an open-source automatic speech recognition model developed by OpenAI. It transcribes spoken audio into text, supports multiple languages, and is robust to noise, making it suitable for developers and researchers building speech-to-text applications.

Whisper Large V2 is a robust automatic speech recognition model trained on 680,000 hours of multilingual and multitask supervised data. It supports transcription, translation, and language identification. The model is widely used via the Transformers library for building speech-to-text applications.

Whisper-medium is the 769M parameter version of OpenAI's Whisper speech recognition model family. It performs automatic speech recognition, language identification, and translation across many languages. The model is provided as open weights on Hugging Face and is widely used via the Transformers library for transcription and related audio tasks.

openai/whisper-tiny.en is the smallest English-only variant of OpenAI's Whisper automatic speech recognition model. It converts English audio into text with high accuracy while using minimal computational resources. Hosted on Hugging Face, it is widely used for testing, research, and lightweight transcription applications.

openai/whisper-base is an open-source automatic speech recognition (ASR) model that transcribes audio files into text. It supports multiple languages and is designed for developers and researchers working on speech-to-text applications. The model is easy to integrate into Python workflows.

openai/whisper-large-v3-turbo is an advanced open-source speech recognition model that provides high-accuracy transcription for audio files in multiple languages. It is designed for developers and researchers building speech-to-text solutions and integrates easily with Python-based workflows.

Systran/faster-whisper-small is an open-source speech recognition model converted from OpenAI's Whisper, optimized for use with CTranslate2. It enables fast and accurate transcription of audio files into text for developers and researchers.

This is a fine-tuned version of OpenAI's Whisper Small model specialized for Cantonese (zh-HK). It performs automatic speech recognition on Cantonese audio. The model is hosted on Hugging Face and follows the standard Whisper pipeline for inference.

faster-whisper-small-int8 is an optimized, INT8-quantized version of the OpenAI Whisper small model for speech-to-text. Created by the Rhasspy team, it is designed for efficient local inference with significantly reduced memory usage and faster performance while maintaining good transcription accuracy. It is available on Hugging Face for use with Transformers or faster-whisper libraries.

whisper-tiny.en is a highly optimized English-only version of OpenAI's Whisper model converted by Xenova for ONNX Runtime. It enables fast, local speech recognition in web and Node.js environments without requiring large model downloads.

Whisper is a web application that enables users to transcribe or translate spoken audio into written text. Users can upload audio files, record directly, or provide YouTube links, and receive accurate transcriptions or translations. It is ideal for content creators, journalists, and researchers.

This repository provides GGUF quantized versions of OpenAI's Whisper-medium model for use with transcribe.cpp and other GGUF-compatible runtimes. It supports transcription in 99 languages and can run efficiently on consumer hardware without requiring cloud services.

This is a GGUF-quantized version of OpenAI's Whisper Large V3 model optimized for use with transcribe.cpp. It supports automatic speech recognition across 100 languages. The quantized formats enable efficient local inference on consumer hardware while maintaining high transcription quality.

Xenova/whisper-tiny provides a browser-compatible version of OpenAI's Whisper tiny model using ONNX and Transformers.js. It enables client-side automatic speech recognition directly in web applications without sending audio to external servers. The model is optimized for low-resource environments and can be used via npm in any JavaScript or TypeScript project.