efficient-nlp

stt-1b-en_fr-quantized

efficient-nlp/stt-1b-en_fr-quantized

stt-1b-en_fr-quantized is a automatic speech recognition model from efficient-nlp. Use it when you need speech turned into text. It is set up for moshi. The card lists the license as cc-by-4.0.

This is a quantized version of Kyutai’s stt-1b-enfr model. The original model is a 1B parameter streaming speech-to-text model for English and French. This fork contains the same model, quantized to Q80 and Q4K GGUF f…