mistralai
/

Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition

voxtral_realtime

Model card Files Files and versions

Resources

View closed (12)

i want to adapt this model for low resource african language for that i have collected the data

#27 opened 2 days ago by

teeofftechnologies

Optimize GPU KV cache memory usage

#25 opened 3 days ago by

Can you train indic (indian) set of languages?

#24 opened 4 days ago by

How to add another language ?

#22 opened 7 days ago by

TheRealTancrede

do not need config.json ?

#18 opened 9 days ago by

[Transformers Integration] Understanding Voxtral Realtime architecture for porting

#17 opened 11 days ago by

AssertionError: rope can only used in combination with a sliding window

#15 opened 13 days ago by

Running on vLLM 0.15.x + Blackwell CUDA 13

#14 opened 13 days ago by

diarization support?

#13 opened 13 days ago by

Reducing time-to-first-token below 1s for conversational use?

#11 opened 15 days ago by

How to make sure transcription_delay_ms is changed when serving with vLLM?

#10 opened 15 days ago by

goncalomcorreia

Error when running on AMD with Docker

#9 opened 16 days ago by

Problem with super long audio

#5 opened 17 days ago by

Installation Video and Testing - Step by Step

#3 opened 17 days ago by

No transcription_delay param in either tekken or params

#2 opened 17 days ago by