Very low RPS of SeamlessM4t model during load test
1
#27 opened 3 months ago
by
gangen
Seamless-M4T.cpp Ggml
#26 opened 7 months ago
by
iHaag
How to process long audio for s2st?
#23 opened 10 months ago
by
Atharva-solanki
Batch Inference
1
#21 opened 11 months ago
by
leonardo-avila
![](https://cdn-avatars.huggingface.co/v1/production/uploads/60aaddf3af553873e6d96cec/7VZGmJ5fvrMqum9Pz2TgJ.jpeg)
Frequent Appearance of <unk> Tokens in Translations to Mandarin (cmn & cmn_Hant) and Cantonese (yue)
#20 opened 12 months ago
by
tanshuai
Let's talk about the performance implications of using dual cards, such as the RTX 3090
#19 opened 12 months ago
by
anhlht
Can i clone my voice for text to speech
3
#17 opened 12 months ago
by
murthy1998
AWS Sagemaker
#16 opened 12 months ago
by
rvryan
Downloaded multitask_unity_large.pt, how can I use it
2
#14 opened about 1 year ago
by
davidlandeo
Can't give torch.Tensor Input
1
#13 opened about 1 year ago
by
ehmargondal
Why is it extracting a summary from longer texts?
1
#12 opened about 1 year ago
by
martincpt
Is anyone working on MPS version or alternative implementation?
#10 opened about 1 year ago
by
joorei
problem installing fairseq2n
1
#9 opened about 1 year ago
by
joorei
What is the max token length for text input?
4
#8 opened about 1 year ago
by
kk3dmax
Example Colab Notebook
1
#7 opened about 1 year ago
by
r3gm
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63e6e242b6a40bf941e520d5/-T6LxA2WbWpgXZKGWqr9T.jpeg)
I may have missed it, but what does <speech_units> mean?
#6 opened about 1 year ago
by
BwandoWando
link installation
1
#4 opened about 1 year ago
by
NickyNicky
![](https://cdn-avatars.huggingface.co/v1/production/uploads/641b435ba5f876fe30c5ae0a/OknUuweWxX3IzUZIKZ6CF.png)