parakeet-ctc-0.6b-Vietnamese
To transcribe with timestamps: python output = asr_model.transcribe('path_to_audios' # by default, timestamps are enabled for char, word and segment level word_timestamps = output0.timestamp'word' # word level timestamps for first sample segment_timestamps = output0.timestamp'segment' # segment level timestamps char_timestamps = output0.timestamp'char' # char level timestamps.
audio → text · made by NVIDIA
Sold by
Nobody in the catalogue publishes a price for this yet.
About
parakeet-ctc-0.6b-Vietnamese — a text model from NVIDIA.
It takes audio and returns text. It was published in January 2026. The catalogue files it under transcribe. Its weights are published under the other licence, which attaches conditions the plain open licences do not.
Every current figure
- Maker
- NVIDIA
- Register
- model
- Takes
- audio
- Returns
- text
- Published
- January 2026
- Parameters
- 600 million · read from its own name
- Licence
- other
Known as 1 name
nvidia/parakeet-ctc-0.6b-Vietnamese