Issues
- 0
- 0
Unable to Download wavLLM Due to Error
#83 opened by minkyu119 - 1
- 0
- 3
- 2
SpeechUT does not have a link for download
#81 opened by world1tree - 9
Error in loading WavLLM model
#78 opened by rishabh004-ai - 5
WavLLM checkpoint
#76 opened by ming024 - 0
- 1
Single Task Training
#77 opened by yangjiabupt - 1
British English TTS model
#69 opened by omega3 - 2
- 4
是否支持中文转语音?
#65 opened by xxm1668 - 1
How to setting language when do S2T
#66 opened by nhha1602 - 1
Baseline implementation
#67 opened by ussenuk - 0
Does the pre-trained model for hidden unit tokenizer use speaker embeddings?
#73 opened by Kodhandarama - 2
extract transorformer layer feature
#74 opened by zbpjlc - 2
Getting TTS output voice close to the training data - Finetuning on different language
#57 opened by Srija616 - 1
The size of tensor a (674) must match the size of tensor b (600) at non-singleton dimension 1
#64 opened by poojitharamachandra - 4
SpeechT5-tts fine-tuned on Chinese
#49 opened by qlmbeck - 4
pretrain loss
#56 opened by MarsMeng1994 - 0
- 0
Link to train_960.tsv is broken
#71 opened by Kodhandarama - 0
"SpeechT5" on Android OS
#70 opened by taeyeonlee - 2
how to pause between two words ?
#43 opened by hulk10425 - 0
Text feature extraction using SpeechLM
#68 opened by wonjune-kang - 1
SpeechT5 - TTS - Tokenizer adding `▁` token between newly added Vietnamese characters
#63 opened by GinUTE - 6
SpeechT5: extracting Chinese speaker embedding
#50 opened by QQ-777777 - 0
- 0
Is end-to-end S2ST possible with Speecht5?
#61 opened by elia-ashraf - 0
Generate the N-best (top few) hypotheses
#60 opened by cyfer0618 - 0
Reproduce ASR experiment results in Hugging Face
#59 opened by jjyaoao - 2
- 2
SpeechLM
#46 opened by blueblue-bubble - 5
SpeechT5:how much epoch is set
#45 opened by QQ-777777 - 11
how to fine tune sid on pretrained model?
#42 opened by haha010508 - 1
[SpeechLM] About phoneme tokenizer in detail?
#40 opened by yuseungwoo - 3
Pretrain SpeechT5 on my own dataset
#38 opened by hungker - 1
Missing speecht5 task
#37 opened by maximerenou - 2
SpeechT5 Speech Enhancement
#36 opened by avramandrei - 0
- 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 opened by Lemonaddeee - 1
SpeechUT inference error in en_fr checkpoint
#52 opened by ytf-philp - 5
SpeechT5 pretrain
#30 opened by benyang0506 - 0
Using SpeechT5 Large for TTS
#51 opened by imranmaj - 1
Fine-tunning on Hugging Face
#35 opened by ramonsanabria - 0
hydra fine-tunning for speechT5?
#41 opened by ramonsanabria - 2
reproduction steps for inference
#39 opened by awgr - 3
SpeechUT inference and fine-tune problem
#34 opened by ytf-philp - 2
SpeechT5: Finetuned SID model
#31 opened by entn-at