Resources

Streaming microphone transcription emits Unicode replacement characters for Chinese text

#49 opened about 1 month ago by

zhengsihua

[audio.cpp] C++/GGML based Voxtral Mini 4B Realtime impl. 16.39x (0.0610 RTF) realtime offline, 170ms TTFT streaming on RTX 5090

🔥❤️ 1

#48 opened 2 months ago by

audio-cpp

Unable to reproduce benchmarks

➕ 1

#47 opened 2 months ago by

abhinavkulkarni

Feature request: distilled per-language "Voxtral Micro" models for edge/on-device use Context

#46 opened 2 months ago by

MaxOnAMission

Add localvoxtral (macOS dictation app) to Community Contributions

#45 opened 2 months ago by

T0mSIlver

What is the expected ratio of GPU memory and KV cache tokens for this model?

#44 opened 2 months ago by

h01-10w

Training dataset size

#43 opened 4 months ago by

ojo

Telephony ASR

#41 opened 5 months ago by

deeksha5

model support per CrispASR — pure C++ inference with GGUF quantisation

👍 1

#40 opened 5 months ago by

cstr

timestamp

#39 opened 5 months ago by

Sh1man

vllm crashing on 0.19.0

#38 opened 5 months ago by

evilperson068

Add Open ASR Leaderboard evaluation results

#37 opened 6 months ago by

SaylorTwift

Questions about training techniques

👀 2

#36 opened 6 months ago by

funnyice

Voxtral Transformers path: chat template fails ("Can't compile non template nodes") and fallback output is garbled

#35 opened 6 months ago by

PierrunoYT

Upload top_20_wavs.zip

#33 opened 7 months ago by

austinv5040

Recommendations

🔥 6

#32 opened 7 months ago by

liuyt6515

سلام

#31 opened 7 months ago by

noor18298

Dont forget to do "audio.resample(processor.feature_extractor.sampling_rate)" if adapt streaming example to your needs

#30 opened 7 months ago by

trevol

punctuation marks

#28 opened 7 months ago by

liuyt6515

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

#27 opened 7 months ago by

teeofftechnologies

Can you train indic (indian) set of languages?

#24 opened 7 months ago by

trysem

How to add another language ?

#22 opened 7 months ago by

TheRealTancrede

do not need config.json ?

#18 opened 7 months ago by

Xiakj

[Transformers Integration] Understanding Voxtral Realtime architecture for porting

#17 opened 7 months ago by

Seungyoun

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

#15 opened 7 months ago by

andres-llms

Running on vLLM 0.15.x + Blackwell CUDA 13

#14 opened 7 months ago by

avblex

diarization support?

🚀👍 7

#13 opened 7 months ago by

evewashere

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

#11 opened 7 months ago by

jloganolson

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

#10 opened 8 months ago by

goncalomcorreia

Error when running on AMD with Docker

#9 opened 8 months ago by

wetchoc

Problem with super long audio

👍 2

#5 opened 8 months ago by

mrigankr

Installation Video and Testing - Step by Step

👍 1

#3 opened 8 months ago by

fahdmirzac

No transcription_delay param in either tekken or params

#2 opened 8 months ago by

mrigankr