nvidia/parakeet-tdt-0.6b-v2

#56 opened about 1 month ago by

ysdede

Segmentation fault (core dumped)

#55 opened about 2 months ago by

zhouxinxin

Outputs words when silence is input to it. How to stop this?

#54 opened about 2 months ago by

polonuim210

Information on finetuning the model for new langauges!!

#53 opened about 2 months ago by

gude

Conversion to TensorRT?

#52 opened about 2 months ago by

shannu122

Word boosting for TDT models

👀 1

#51 opened about 2 months ago by

hoavu1234

how does the model handle timestamp decoding ?

👍 1

#50 opened about 2 months ago by

StephennFernandes

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

3

#48 opened 2 months ago by

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

#47 opened 3 months ago by

pronoobie

OutOfMemoryError: CUDA out of memory. on RTX A5000

#46 opened 3 months ago by

akskuchi

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

❤️ 7

#45 opened 3 months ago by

pronoobie

how to load the model from local directory?

#44 opened 3 months ago by

ALu7

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

❤️ 🔥 2

#43 opened 3 months ago by

pronoobie

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

👍 ❤️ 5

6

#41 opened 3 months ago by

WJ88

How should I start word-level timestamp？

#40 opened 3 months ago by

ppoudd

Speaker Diarization ??

👍 2

#39 opened 3 months ago by

vasanth5596

Word boosting / context biasing

8

#34 opened 3 months ago by

hoavu1234

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 3 months ago by

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

#32 opened 3 months ago by

parakeet as a local MCP server

❤️ 1

#31 opened 3 months ago by

alexmnahas

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

#30 opened 3 months ago by

Flyingcrabs

Is the model capable of splitting different speakers?

👀 1

#29 opened 3 months ago by

BigDeeper

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

#27 opened 3 months ago by

Model initialization

#22 opened 4 months ago by

Homin

Bug report

👍 1

#20 opened 4 months ago by

JustinRocks

Is CUDA supported when running on Jetson Orin?

#19 opened 4 months ago by

kikaitachi

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

#18 opened 4 months ago by

jacktol

Only English is supported?

#17 opened 4 months ago by

wangleineo

Does this model identifies speaker?

👀 1

8

#16 opened 4 months ago by

SouravAhmed

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

6

#15 opened 4 months ago by

will1130

New Language Training

👀 🔥 8

6

#11 opened 4 months ago by

ali-amiri

What is the data format for training?

5

#10 opened 4 months ago by

ONNX conversion

16

#9 opened 4 months ago by

Berrisius

Ignores repeated words

#8 opened 4 months ago by

HeadlessBandit

Finetuning With Custom Data Tutorial

#7 opened 4 months ago by

SirCodesAlot

A German Version would be fantastic!

3

#6 opened 4 months ago by

Buttermilk03

We clearly need a french version

👍 2

#4 opened 4 months ago by

Sarwg

Streaming?

➕ 8

12

#3 opened 4 months ago by

pscar

Please do It for Japanese

👍 1

#2 opened 4 months ago by

riken12

Local Installation Video and Testing - Step by Step

👍 3