Mms Zeroshot 300m
A checkpoint model based on the MMS zero-shot project, capable of transcribing speech in nearly any language with only a small amount of unannotated text in the target language.
Downloads 48
Release Time : 7/30/2024
Model Overview
This model is a multilingual speech recognition system that maps a small amount of target language text to an intermediate representation, combined with an optional language model to transcribe new languages.
Model Features
Zero-shot speech recognition
Transcribes speech in new languages with only a small amount of unannotated text in the target language.
Multilingual support
Supports speech recognition in 1,150 languages, covering a wide range of languages.
Intermediate representation transcription
Outputs transcription results in an intermediate representation (uroman notation) for further processing.
Model Capabilities
Multilingual speech recognition
Zero-shot learning
Speech transcription
Use Cases
Speech transcription
Multilingual speech transcription
Transcribes speech in different languages into text, suitable for speech processing in multilingual environments.
Highly accurate transcription results supporting multiple languages.
Language learning
Language learning assistance
Helps language learners study pronunciation and spelling in new languages through speech recognition.
Provides accurate speech-to-text conversion to aid learning.
Featured Recommended AI Models
Š 2025AIbase