|
Bert for audio classification
|
|
0
|
689
|
April 25, 2022
|
|
Extracting information from bills, tax statements, etc: What ML model to use?
|
|
2
|
855
|
April 23, 2022
|
|
Confidence Scores / Self-Training for Wav2Vec2 / CTC models With LM (PyCTCDecode)
|
|
1
|
1332
|
April 21, 2022
|
|
Confidence Scores / Self-Training for Wav2Vec2 / CTC models
|
|
1
|
1371
|
April 21, 2022
|
|
Text to Speech Alignment with Transformers
|
|
2
|
1082
|
April 20, 2022
|
|
Projected gradient descent on autoregressive models
|
|
0
|
624
|
April 19, 2022
|
|
Masked Language Model Scoring
|
|
3
|
1477
|
April 16, 2021
|
|
Compute metric on Dev
|
|
1
|
653
|
April 15, 2022
|
|
Why are huge batch sizes used for pretraining and small ones for finetuning?
|
|
2
|
1848
|
April 12, 2022
|
|
Text similarity not by cosine similarity
|
|
3
|
1878
|
April 12, 2022
|
|
Aggregate encoder states in encoder-decoder models for long sequences?
|
|
0
|
575
|
April 8, 2022
|
|
Why do the commit histories of Hugging Face's datasets and models appear recent? Weren't these datasets and models uploaded a while ago?
|
|
2
|
574
|
April 8, 2022
|
|
Incorporating structural information in a Transformer?
|
|
0
|
586
|
April 6, 2022
|
|
Can you use both copy mechanism and BPE for a NMT task?
|
|
0
|
556
|
April 6, 2022
|
|
Is there an easy way to apply layer-wise decaying learning rate in huggingface trainer for RobertaMaskedForLM?
|
|
3
|
1379
|
April 5, 2022
|
|
The discussion is about entity recognition and corefrence resolution
|
|
0
|
566
|
March 25, 2022
|
|
GPT2 for QA Pair Generation
|
|
9
|
4135
|
March 23, 2022
|
|
Converting Test Case Description into Test case Steps
|
|
0
|
600
|
March 4, 2022
|
|
Best Pre-training Strategy
|
|
0
|
595
|
March 3, 2022
|
|
Relative Position Representation/Encoding for Transformer
|
|
0
|
949
|
February 22, 2022
|
|
How find idea for academic thesis?
|
|
2
|
665
|
February 19, 2022
|
|
Extractive oracle
|
|
0
|
666
|
February 9, 2022
|
|
A Survey to Understand Challenges of Deploying Text Classification
|
|
2
|
656
|
February 8, 2022
|
|
Question Answering model on mathematical domain for the greek language
|
|
0
|
591
|
February 1, 2022
|
|
Finetuning German BERT for QA on biomedical domain
|
|
2
|
786
|
January 30, 2022
|
|
[Suggestions and Guidance]Finetuning Bert models for Next word Prediction
|
|
4
|
1229
|
January 26, 2022
|
|
Suggestions for an open source tagging tool to build custom LayoutLMv2 datasets
|
|
0
|
609
|
January 25, 2022
|
|
Paper Notes: Deepspeed Mixture of Experts
|
|
2
|
1112
|
January 20, 2022
|
|
Using mixup on RoBERTa
|
|
6
|
1348
|
July 21, 2020
|
|
How does the vocabulary size count towards total parameter size of a model?
|
|
0
|
776
|
January 18, 2022
|