rhasspy/piper-voices · Discussions

Update en/en_US/kusal/medium/MODEL_CARD

#55 opened about 1 month ago by

Update en/en_US/amy/medium/MODEL_CARD

#54 opened about 1 month ago by

Update en/en_US/amy/low/MODEL_CARD

#53 opened about 1 month ago by

Update en/en_US/l2arctic/medium/MODEL_CARD

#52 opened about 1 month ago by

213435

#51 opened about 2 months ago by

Manoskaliv

1234345

#50 opened about 2 months ago by

Manoskaliv

https://huggingface.co/rhasspy/piper-voices/tree/main

#49 opened about 2 months ago by

PUREDNA

Contribution: AF_Heart voice from Kokoro

#47 opened 4 months ago by

ken107

webaudioproject

#46 opened 4 months ago by

jtorreseco

How to add new voices TTS ? (im confussed)

#44 opened 4 months ago by

Buffet13

👉 “Request: Female Hinglish Voice Model for Piper”

#43 opened 4 months ago by

AAMIR900

persian gyro checkpoint

#42 opened 4 months ago by

gyroing

请问有时间可以把韩语，日语，孟加拉的几种音频也弄上吗

#41 opened 4 months ago by

AILIS1

Please add bahasa indonesia

5

#40 opened 5 months ago by

amrikhsn

Meidum quality DE (German) Voice

#38 opened 5 months ago by

hmzblgngg

Contribution: "Daniela" Voice Trained with Piper on OpenSLR Dataset

#35 opened 7 months ago by

larcanio

Upstream URL link to zh_CN huayan is dead

1

#34 opened 7 months ago by

ShamrockLee

PyTorch Files

#30 opened 10 months ago by

Ubikare

Unable to use en_US-ljspeech-medium model,

#28 opened 10 months ago by

pHHHH

Bug with Greek voice: incomprehensible output

#27 opened 11 months ago by

Shine-neko

Bad sound with less words (french)

#26 opened 12 months ago by

Touf2638

pt_PT language fails to download `piper --model pt_PT-tugão-medium`

#21 opened about 1 year ago by

ricardoamaro

how can we add hindi language support

👀 👍 4

3

#18 opened over 1 year ago by

nagAA22

Add Latvian language support

#17 opened over 1 year ago by

BlindDeveloper

Piper recording studio dataset reference

🚀 1

#14 opened over 1 year ago by

paolapersico1

nl_NL-mls-medium voice output is weird

#13 opened over 1 year ago by

BramNH

What is the source for the Danish dataset?

#12 opened over 1 year ago by

mabsdk

Is there a way to post an additional output array of floats for Phoneme Timings?

1

#9 opened almost 2 years ago by

STFUnity

previewing samples in order

#8 opened almost 2 years ago by

dumnone

en_US/Ryan can't pronounce 9/11 as "nine eleven"

3

#3 opened about 2 years ago by

iconoclasthero

speaker ids does not match the samples generated.

#2 opened over 2 years ago by

mirfan899

Question on libritts