SpeechT5
The SpeechT5 framework consists of a shared seq2seq and six modal-specific (speech/text) pre/post-nets that can address a few audio-related tasks.
Microsoft
company
Verified
Research interests
None defined yet.
Collections
1
models
254
microsoft/cvt-13
Image Classification
•
Updated
•
6.58k
•
5
microsoft/prophetnet-large-uncased-squad-qg
Text2Text Generation
•
Updated
•
298
•
5
microsoft/phi-1_5
Text Generation
•
Updated
•
25.5k
•
665
microsoft/swin-tiny-patch4-window7-224
Image Classification
•
Updated
•
12.1k
•
17
microsoft/tapex-large-sql-execution
Table Question Answering
•
Updated
•
4.4k
•
9
microsoft/git-base-vatex
Text Generation
•
Updated
•
963
•
1
microsoft/mpnet-base
Fill-Mask
•
Updated
•
24.2k
•
20
microsoft/xclip-base-patch16-zero-shot
Feature Extraction
•
Updated
•
11.9k
•
15
microsoft/phi-1
Text Generation
•
Updated
•
1.95k
•
80
microsoft/swin-base-patch4-window7-224
Image Classification
•
Updated
•
6.16k
•
3