Whisper-base.en is a pre-trained English-only automatic speech recognition (ASR) model from the OpenAI Whisper family. It converts audio speech into text with high accuracy and robustness to background noise, different accents, and technical language. Available on Hugging Face, the model can be used for transcription, translation, and other audio understanding tasks either locally or through inference providers. It serves as a foundational model for developers building voice applications.
Whisper Base.en sits in PulseGate's Voice, TTS & speech category. Accurately transcribing spoken English audio into text across varied conditions and accents. Whisper Base.en is an open-source project aimed at developers and researchers. The project is open source (MIT). Whisper Base.en is available on the web and API.
Behind Whisper Base.en is OpenAI, based in the United States, and it first shipped in 2022. Development happens publicly on GitHub with 106.5k stars and 2 commits in the last 90 days. Key capabilities include Speech Recognition, English Transcription, and Multilingual Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do