issues
search
microsoft
/
SpeechT5
Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
MIT License
1.09k
stars
113
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
SpeechT5: Finetuned SID model
#31
entn-at
closed
1 year ago
2
SpeechT5 pretrain
#30
benyang0506
opened
1 year ago
5
About the SpeechT5 pre-training curve
#29
benyang0506
closed
1 year ago
4
SpeechT5 Pretrain ERROR
#28
benyang0506
closed
1 year ago
1
Whether fp16 is enabled in VATLM during pre-training
#27
xiabingquan
closed
1 year ago
2
SpeechLM:KeyError: 'text_transformer' while initing the SpeechLMConfig
#26
JunZhan2000
closed
1 year ago
2
VATLM: ModuleNotFoundError: No module named 'fairseq.data.audio.multi_corpus_dataset_audio'
#25
xiabingquan
closed
1 year ago
6
Same benchmark, same architecture, but the WER is differenet, why?
#24
splinter21
closed
1 year ago
2
SpeechLM: How to train 'Phone-unit tokenizer for speech' using kaldi?
#23
YWMditto
closed
1 year ago
7
Speech2C "Inf detected in output" while training
#22
Sreyan88
closed
1 year ago
4
Speech2C training error
#21
Sreyan88
closed
1 year ago
6
Missing SPM and Vocabulary files
#20
sumanthd17
closed
1 year ago
2
Port to Huggingface
#19
StephennFernandes
closed
1 year ago
1
SpeechLM: How to resample phonemes' frame rate from 30ms to 20ms?
#18
Arrivederci
closed
1 year ago
3
SpeechLM: how to prepare phoneme sequence for T2U generator
#17
cwang621
closed
1 year ago
5
SpeechT5: How to get speaker embeddings ?
#16
Arrivederci
closed
1 year ago
12
Example values for finetuning asr
#15
YWMditto
closed
1 year ago
18
Sample Rates are different between speech pre-training dataset and tts dataset
#14
Maggione
closed
1 year ago
1
Combining speech and text in the encoder
#13
jacqle
closed
1 year ago
1
Can you provide a voice conversion finetune recipe?
#12
hpjang
closed
1 year ago
2
This repo is missing important files
#11
microsoft-github-policy-service[bot]
closed
1 year ago
0
Adding Microsoft SECURITY.MD
#10
microsoft-github-policy-service[bot]
closed
1 year ago
0
Text data preparation
#9
tskim9439
closed
1 year ago
3
No code for Speech Synthesis
#8
petervickers
closed
1 year ago
4
ArgumentError in SpeechT5Task.add_args() when running fairseq-generate
#7
busukxuan
closed
2 years ago
1
Does the quantizer is used when fine-tune the pretrained backbone for the downstream task ?
#6
zhhao1
closed
2 years ago
2
Difficulties loading pre-trained weights!
#5
sanchit-gandhi
closed
2 years ago
2
Missing text_to_speech_dataset.py in speecht5/data
#4
ayushtues
closed
2 years ago
1
How to load the pretrained models in pytorch
#3
ayushtues
closed
2 years ago
5
Are you planning to open source the configuration of the baselines and downstream tasks?
#2
Maggione
closed
2 years ago
1
how to pre-train on a custom dataset ?
#1
StephennFernandes
closed
2 years ago
16
Previous