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 Medium sits in PulseGate's Voice, TTS & speech category. It focuses on converting spoken audio in multiple languages into accurate text transcriptions. It is built as an open-source project for developers. Whisper Medium is open source under the MIT license. It runs on the web and API.
Behind Whisper Medium is OpenAI, and the product first shipped in 2022. Development happens publicly on GitHub with 105.3k stars. Key capabilities include speech recognition, multilingual support, and transcription.
Latest indexed changes and source events
openai/whisper-medium verified by the PulseGate indexer
Other apps tracked under the same category.
