Whisperkit Coreml Alternatives

ParakeetKit Pro provides optimized speech recognition models compatible with WhisperKit and the Argmax Pro SDK. The models are quantized and compressed for local, on-device inference on Apple silicon. It includes a Homebrew CLI tool for easy transcription of audio files directly on macOS devices without requiring internet connectivity.

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.

whisper-small is an open-source automatic speech recognition model developed by OpenAI. It supports multilingual audio transcription and is suitable for developers and researchers building speech-to-text applications. The model can be fine-tuned and deployed locally or via API for various audio processing tasks.

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.

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.

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.

Xenova/whisper-base.en is a converted and optimized version of OpenAI's Whisper base model for English speech recognition. It is designed for use with Transformers.js and ONNX Runtime, enabling speech transcription to run locally in web browsers and Node.js environments. The model provides a lightweight alternative for English-only automatic speech recognition tasks.

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.

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.

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.