nvidia
/

parakeet-tdt-0.6b-v3

Automatic Speech Recognition

feature-extraction

hf-asr-leaderboard

Eval Results (legacy)

Model card Files Files and versions

Resources

View closed (8)

A quantized and deployable version of the model on Nvidia Orins with TensorRT

#44 opened 23 days ago by

The model sometimes drops full sentences

#42 opened about 1 month ago by

CUDA out of memory with long audio

#41 opened about 2 months ago by

Model support per CrispASR — pure C++ inference with GGUF (no Python/NeMo needed)

#38 opened about 2 months ago by

Add Open ASR Leaderboard evaluation results

#36 opened 2 months ago by

Environment setup

#35 opened 2 months ago by

Inconsistent number transcription - often letters instead of digits (french language)

#34 opened 3 months ago by

requirements.txt ? What Python version does this need?

#33 opened 3 months ago by

eror timestamp

#32 opened 4 months ago by

Word boosting/Custom vocabulary

#31 opened 5 months ago by

I want transcription not translation

#29 opened 6 months ago by

Update Readme

#27 opened 7 months ago by

How to specify the output language?

#26 opened 7 months ago by

Will there be support for other languages?

#25 opened 7 months ago by

First 273 vocabulary tokens

#24 opened 7 months ago by

Does it support Realtime ?

#23 opened 7 months ago by

Separate languages into distinct models. How?

#22 opened 7 months ago by

Running parakeet-tdt-0.6b-v3 on Jetson AGX Orin, Thor, or Spark!

#21 opened 7 months ago by

Seeking a Clear Tutorial for Fine-Tuning NVIDIA NeMo Models on New English Audio Domains

#19 opened 8 months ago by

Streaming question

#18 opened 8 months ago by

training script

#17 opened 8 months ago by

[EXAMPLE] Working streaming POC with Gradio MIC input.

#16 opened 8 months ago by

Can support for Irish Gaelic be added?

#15 opened 9 months ago by

Fine-tune on the other Language

#14 opened 9 months ago by

Questions about streaming with Parakeet and TDT merging methods

#13 opened 9 months ago by

Missing sentences when transcribe some audios

#12 opened 9 months ago by

Streaming?

#11 opened 9 months ago by

Question about inference speed

#10 opened 10 months ago by

Async streaming container?

#9 opened 10 months ago by

Is it possible to prompt or output language?

#8 opened 10 months ago by

Local Installation Video and Testing - Step by Step

#6 opened 10 months ago by

Japanese support plan?

#5 opened 10 months ago by

Recognise separate voices

#4 opened 10 months ago by

Word boosting

#3 opened 10 months ago by

training hyper-parameters

#2 opened 10 months ago by

Code switching

#1 opened 10 months ago by