Nvidia releases an open speech model that transcribes 40 languages
Nvidia released Nemotron 3.5 Transcribe, a free open-weight model capable of transcribing audio in 40 languages and translating 31 of them. The model can also identify and label up to eight speakers in recordings up to an hour long. The release includes Granary v2, a dataset comprising 463,062 hours of speech data across 48 languages.
Key points
- Transcribes 40 languages, translates 31
- Identifies up to 8 speakers in hour-long recordings
- Granary v2 dataset with 463,062 hours of multilingual speech
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. The Next Web did the reporting; read the original for the full story.
Read the full story at The Next Web
