nari-labs/Dia-1.6B · Discussions

Dia 1.6B — the future of mobile TTS

#75 opened 3 months ago by

3morixd

How to improve inference speed ?

3

#74 opened 11 months ago by

Anilosan15

Update README.md

#73 opened about 1 year ago by

Khangee07

How can this model support Indonesian?

#72 opened about 1 year ago by

Syams

timestamps

#71 opened about 1 year ago by

Sureguy

Other languages

1

#70 opened about 1 year ago by

marek192

How to control the "speed_factor" while model.generate?

👍 2

1

#69 opened over 1 year ago by

SekarKrishnan

RuntimeError: Error loading model from Hugging Face Hub (nari-labs/Dia-1.6B)

3

#68 opened over 1 year ago by

raysongraysong

Run Dia-1.6B TTS model via Google Ai Edge Gallery

#67 opened over 1 year ago by

axelis

Rename README.md to README.mdh

#66 opened over 1 year ago by

Sam1290

Update README.md

#65 opened over 1 year ago by

Sam1290

Update README.md

#64 opened over 1 year ago by

Sam1290

Voice clone?

2

#63 opened over 1 year ago by

overkast

Missing dac module when running Dia

➕ 2

#62 opened over 1 year ago by

TheGreatDumbDumb

Upload IMG_1028.png

#61 opened over 1 year ago by

Aldiannnnn05

Upload 8 files

#60 opened over 1 year ago by

mickey58

Upload Test.txt

#59 opened over 1 year ago by

mickey58

CPU Functionality (I will maintain the patience of a gamete waiting to be set free - from its ascetic monk's blue sack)

2

#58 opened over 1 year ago by

Choppie-Chaz

Getting inconsistent audio for short texts.

1

#57 opened over 1 year ago by

Shishir17

Option to output speakers to different audio files

#55 opened over 1 year ago by

deepcrunch

Update README.md

#54 opened over 1 year ago by

Imsibasankar

Update README.md

#53 opened over 1 year ago by

nguyenphucvu

smaller version of the model that can run on device

#52 opened over 1 year ago by

stopthinking

test

#51 opened over 1 year ago by

vamp94

Upload your_voice.wav

#50 opened over 1 year ago by

Emmylahot12

Any way of controling the voice?

4

#49 opened over 1 year ago by

AndresFMR

Please add this model to huggingchat as a community tool

#48 opened over 1 year ago by

devopsML

Create preprocessor.json

1

#47 opened over 1 year ago by

faizandigi009

Create preprocessor.json

#46 opened over 1 year ago by

faizandigi009

Upload preprocessor.json

#45 opened over 1 year ago by

faizandigi009

Create preprocessor_config.json

#43 opened over 1 year ago by

faizandigi009

is it possible to inference on gtx 1600ti (laptop) with cuda or without cuda

1

#42 opened over 1 year ago by

fatihhangulec

AMD Support?

1

#40 opened over 1 year ago by

Avaredra

Add normal pip dependencies

❤️ 1

6

#35 opened over 1 year ago by

nikich340

Is this model compatible with TPU

1

#33 opened over 1 year ago by

ycjian

[REQ] Please also add some other supports

👍 3

2

#29 opened over 1 year ago by

dattazigzag

Make it run on GTX1080, works!

👍 3

#27 opened over 1 year ago by

fawo

Paper?

5

#21 opened over 1 year ago by

nightdude

Multiple languages support

👀👍 15

6

#19 opened over 1 year ago by

thunder-007

I created an API wrapper with web UI

❤️🔥 10

6

#13 opened over 1 year ago by

devnen

Does it support SSML?

1

#8 opened over 1 year ago by

spaliwal

guide to run on Windows with CUDA

👍 5

#2 opened over 1 year ago by

froilo

Local Installation Video and Testing - Step by Step

👍 2

#1 opened over 1 year ago by

fahdmirzac