microsoft/speecht5_tts · Discussions

Are there any streaming performance optimization available for this model like precison, torch compile i only see this example?

#47 opened 4 months ago by

lukiggs

Internal Server Error while using Inference API for Speech T5

5

#46 opened 8 months ago by

AK-12

add the import torch line in the below cell

#45 opened 8 months ago by

Waqar07813

How to change voice character [ANSWERED]

5

#44 opened 8 months ago by

MicahB

Support for the Ukrainian language?

#43 opened 9 months ago by

Techn0man1ac

Is there a way to use IPA symbols?

#42 opened 10 months ago by

m-conrad-202

How to Calculate GPU usage for re-training Microsoft/speechT5_tts ?

#41 opened 11 months ago by

huggingfacerohit

[AUTOMATED] Model Memory Requirements

#40 opened 11 months ago by

model-sizer-bot

non-default generation parameters issue

1

#39 opened 12 months ago by

mikhail-panzo

How can I run pretrained model on multi GPUs?

#38 opened about 1 year ago by

NorzY

更改聚个会

#36 opened about 1 year ago by

wuyadamao

Need help with cloning a new voice.

3

#35 opened about 1 year ago by

M4Marvin

How to set language?

#33 opened about 1 year ago by

areumtecnologia

fix typos in links under model sources

#32 opened about 1 year ago by

bwallace

How can I pass the result to microphone

2

#31 opened about 1 year ago by

thunder-007

I cannot over pass this error

#30 opened about 1 year ago by

vividsd

Error 500

1

#29 opened over 1 year ago by

raghuv-aditya

Adding `safetensors` variant of this model

#28 opened over 1 year ago by

SFconvertbot

missing import

#26 opened over 1 year ago by

arnaucas

Is it possible to change Voice Character? if then give a e.g

1

#25 opened over 1 year ago by

wudada

Changing Voice Character

2

#21 opened over 1 year ago by

0xrk

How to use in iPhone?

2

#20 opened over 1 year ago by

AamirFarooq

Adding `safetensors` variant of this model

#19 opened over 1 year ago by

SFconvertbot

A note on preventing model hallucinations

#18 opened over 1 year ago by

mstachow

Working Hacky Code

2

#16 opened over 1 year ago by

JHenzi

Fine Tunning the model

#15 opened over 1 year ago by

dcassine

Update README.md

#14 opened over 1 year ago by

CJacobnriia

model sometimes repeats itself and glitches during speech.

1

#13 opened over 1 year ago by

mstachow

Finetune on Completely New Language

1

#12 opened over 1 year ago by

machinelearningzuu

Changing the way the text is spoken

4

#11 opened almost 2 years ago by

Khabbab

fine-tune on the Chinese

2

#10 opened almost 2 years ago by

YiChenbeck

text-to-speech is not a valid pipeline

9

#7 opened almost 2 years ago by

boddles2

Error when loading SpeechT5Processor from pretrained

2

#5 opened almost 2 years ago by

peterloll

Speech to Speech Translation

1

#3 opened about 2 years ago by

Owos