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
AI & ML interests
None defined yet.
Collections
4
TAPEX is the state-of-the-art table pre-training models which can be used for table-based question answering and table-based fact verification.
-
TAPEX: Table Pre-training via Learning a Neural SQL Executor
Paper • 2107.07653 • Published • 1 -
microsoft/tapex-large-finetuned-wtq
Table Question Answering • Updated • 5.21k • 36 -
microsoft/tapex-base-finetuned-wikisql
Table Question Answering • Updated • 7.82k • 15 -
microsoft/tapex-large-sql-execution
Table Question Answering • Updated • 263 • 13
models
265
microsoft/phi-2
Text Generation
•
Updated
•
150k
•
1.86k
microsoft/phi-1
Text Generation
•
Updated
•
8.81k
•
167
microsoft/BiomedVLP-BioViL-T-Official-Split
Updated
microsoft/trocr-base-handwritten
Image-to-Text
•
Updated
•
249k
•
126
microsoft/layoutlm-base-uncased
Updated
•
1.34M
•
26
microsoft/phi-1_5
Text Generation
•
Updated
•
127k
•
1.19k
microsoft/trocr-large-printed
Image-to-Text
•
Updated
•
35.2k
•
52
microsoft/kosmos-2-patch14-224
Image-to-Text
•
Updated
•
13.4k
•
84
microsoft/DialoGPT-small
Conversational
•
Updated
•
18.2k
•
67
microsoft/table-transformer-structure-recognition-v1.1-pub
Object Detection
•
Updated
•
644