nvidia
/

parakeet-tdt-0.6b-v2

Automatic Speech Recognition

hf-asr-leaderboard

Model card Files Files and versions

Resources

View closed (16)

How can I align timesteps to text for Parakeet-tdt-0.6b-v2 output using KenLM?

#48 opened 14 days ago by

Poor WER when trying to fine-tune Parakeet v2 TDT to other dataset than English

#47 opened 22 days ago by

OutOfMemoryError: CUDA out of memory. on RTX A5000

#46 opened 24 days ago by

Recipes to Finetune to new Language example Hindi (Finally figured out)

#45 opened 24 days ago by

how to load the model from local directory?

#44 opened about 1 month ago by

Use this to fill web forms no typing (STT server)

#43 opened about 1 month ago by

Real-Time Mic Transcription on free 2vCPU - using this model, check it out

#41 opened about 1 month ago by

How should I start word-level timestamp？

#40 opened about 1 month ago by

Speaker Diarization ??

#39 opened about 1 month ago by

Word boosting / context biasing

#34 opened about 1 month ago by

Why does using the same fastconformer_hybrid_tdt_ctc_bpe.yaml config to fine-tune pre-train model result in a "mismatch" error?

#33 opened about 1 month ago by

How can I get timestamps when using KenLM with the model?

#32 opened about 1 month ago by

parakeet as a local MCP server

#31 opened about 1 month ago by

Besides GPU, can any other edge accellerators run it. EX: (Hailo AI Hat for RPI)

#30 opened about 1 month ago by

Is the model capable of splitting different speakers?

#29 opened about 1 month ago by

How can I get the correct y_sequence format as I expect?

#27 opened about 1 month ago by

Model initialization

#22 opened about 2 months ago by

Bug report

#20 opened about 2 months ago by

Is CUDA supported when running on Jetson Orin?

#19 opened about 2 months ago by

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

#18 opened about 2 months ago by

Only English is supported?

#17 opened about 2 months ago by

Does this model identifies speaker?

#16 opened about 2 months ago by

How can I transcribe an audio file that’s longer than an hour when I have only 12 GB of VRAM?

#15 opened about 2 months ago by

New Language Training

#11 opened about 2 months ago by

What is the data format for training?

#10 opened about 2 months ago by

ONNX conversion

#9 opened about 2 months ago by

Ignores repeated words

#8 opened about 2 months ago by

Finetuning With Custom Data Tutorial

#7 opened about 2 months ago by

A German Version would be fantastic!

#6 opened about 2 months ago by

We clearly need a french version

#4 opened about 2 months ago by

Streaming?

#3 opened about 2 months ago by

Please do It for Japanese

#2 opened about 2 months ago by

Local Installation Video and Testing - Step by Step

#1 opened about 2 months ago by