issues
search
microsoft
/
SpeechT5
Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
MIT License
1.21k
stars
114
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Are there any performance optimization for inference available for this model or faster inference versions or streaming I only find this example?
#93
lukaLLM
opened
4 weeks ago
0
Speech conversion: process whole input without stopping
#92
holmbuar
closed
1 month ago
1
gaokao_audio can not be download? something error
#91
liyunlongaaa
opened
2 months ago
1
Why can WavLLM understand audio sounds as well?
#90
BenoitWang
opened
2 months ago
1
Setup Error about WavLLM
#89
XqZeppelinhead0702
opened
2 months ago
4
Request for Assistance with VATLM Implementation: Accessing Wave2Vec Model File
#88
yeonju7kim
opened
2 months ago
0
I found minor typo in Readme
#87
yeonju7kim
opened
2 months ago
0
Please fix the broken download link!!! So many models cann't be used without checkpoint.
#86
world1tree
opened
3 months ago
0
How to fine-tune SpeechT5 HifiGAN vocoder?
#85
yukiarimo
opened
3 months ago
0
soundfile.LibsndfileError: <exception str() failed>
#84
ciwei6107563
closed
3 months ago
0
Unable to Download wavLLM Due to Error
#83
minkyu119
opened
3 months ago
1
What languages are supported? How to specify a language?
#82
secsilm
opened
5 months ago
0
SpeechUT does not have a link for download
#81
world1tree
opened
5 months ago
2
What's the model_path and data_name on inference code?
#80
YepJin
opened
6 months ago
3
Confusion/Question about SpeechT5SpeechDecoderPostnet output
#79
Student204161
opened
6 months ago
0
Error in loading WavLLM model
#78
rishabh004-ai
opened
7 months ago
9
Single Task Training
#77
yangjiabupt
closed
7 months ago
1
WavLLM checkpoint
#76
ming024
opened
7 months ago
5
ASR fine-tuning loss goes to zero after several epochs
#75
yunigma
closed
7 months ago
2
extract transorformer layer feature
#74
zbpjlc
opened
8 months ago
2
Does the pre-trained model for hidden unit tokenizer use speaker embeddings?
#73
Kodhandarama
opened
9 months ago
0
What is the time taken to converge for the hidden unit tokenizer?
#72
Kodhandarama
opened
9 months ago
0
Link to train_960.tsv is broken
#71
Kodhandarama
opened
9 months ago
0
"SpeechT5" on Android OS
#70
taeyeonlee
opened
10 months ago
0
British English TTS model
#69
omega3
closed
7 months ago
1
Text feature extraction using SpeechLM
#68
wonjune-kang
opened
10 months ago
0
Baseline implementation
#67
ussenuk
opened
12 months ago
1
How to setting language when do S2T
#66
nhha1602
opened
1 year ago
1
是否支持中文转语音？
#65
xxm1668
opened
1 year ago
4
The size of tensor a (674) must match the size of tensor b (600) at non-singleton dimension 1
#64
poojitharamachandra
opened
1 year ago
1
SpeechT5 - TTS - Tokenizer adding `▁` token between newly added Vietnamese characters
#63
GinUTE
closed
11 months ago
1
ASR SpeechT5 training - model predicts same output for different inputs
#62
L7uan
opened
1 year ago
1
Is end-to-end S2ST possible with Speecht5?
#61
elia-ashraf
opened
1 year ago
0
Generate the N-best (top few) hypotheses
#60
cyfer0618
opened
1 year ago
0
Reproduce ASR experiment results in Hugging Face
#59
jjyaoao
closed
1 year ago
0
Voice Conversion - Error with Some Mono, 16kHz, 16bit Audio
#58
fabiocat93
opened
1 year ago
3
Getting TTS output voice close to the training data - Finetuning on different language
#57
Srija616
opened
1 year ago
2
pretrain loss
#56
MarsMeng1994
opened
1 year ago
4
Bump scipy from 1.5.4 to 1.10.0 in /VATLM/vat_hubert
#55
dependabot[bot]
opened
1 year ago
0
VATLM: Error when loading finetuned checkpoints for infer_s2s
#54
naraysa
opened
1 year ago
0
Pretraining SpeechT5, meet problems about batch_sampler in multitask_dataset. Should I get idx and bin files of data one by one (wav) or get all of them in only two file(idx and bin each have one)
#53
Lemonaddeee
opened
1 year ago
0
SpeechUT inference error in en_fr checkpoint
#52
ytf-philp
opened
1 year ago
1
Using SpeechT5 Large for TTS
#51
imranmaj
opened
1 year ago
0
SpeechT5: extracting Chinese speaker embedding
#50
QQ-777777
opened
1 year ago
6
SpeechT5-tts fine-tuned on Chinese
#49
qlmbeck
opened
1 year ago
4
add link to Hugging Face fine-tuning example
#48
hollance
closed
1 year ago
1
The link for Prosody-SpeechT5 in the Readme is dead/404
#47
svantana
closed
1 year ago
2
SpeechLM
#46
blueblue-bubble
closed
1 year ago
2
SpeechT5：how much epoch is set
#45
QQ-777777
closed
1 year ago
5
how to pause between two words ?
#43
hulk10425
opened
1 year ago
2
Next