🎓
enjoying hard work!
trying to learn what AI learns
- New Delhi, India
- 09:22
(UTC +05:30) - http://thevasudevgupta.com
- @thevasudevgupta
- in/thevasudevgupta
- https://unboxai.com/
Here is the collection of my open-source work:
Open Source Contributions to HuggingFace:
- Added PyTorch
BigBird-Pegasus
to Transformers - Added PyTorch
BigBird-RoBERTa
to Transformers - Added Flax/Jax
BigBird-RoBERTa
to Transformers - Added script for training
FlaxBigBird
on natural questions to Transformers - Integrated
Microsoft's DeepSpeed
with Accelerate - Added
ModelHubMixin
in Hub
Open Source Contributions to TensorFlow (Google):
- Exported fine-tuned Wav2Vec2 model to TFHub
- Exported pre-trained Wav2Vec2 model to TFHub
- Added notebook for demonstrating Wav2Vec2 fine-tuning to TFHub
- Implemented & trained Wav2Vec2 model in TensorFlow
Blogs/Posters:
- Optimizing adapters for NMT
- Understanding BigBird's Block Sparse Attention
- BioBigBird: Leveraging Entire Articles for Biomedical Language Understanding
Talks/Lectures:
- BigBird: Transformers on long sequences
- Deep Dive into Pre-trained Transformers
- CUDA Concepts YouTube Series
Tutorials:
Flax BigBird
evaluation on natural-questions datasetPyTorch BigBird
evaluation on natural-questions datasetPyTorch BigBirdPegasus
evaluation on PubMed dataset- How to use BigBird (RoBERTa & Pegasus) for inference
- Template for fine-tuning a pre-trained Wav2Vec2 SavedModel
- Conversion of TF Wav2Vec2 model to ONNX and compares the latency of ONNX exported model & TF model on CPU
- Wav2Vec2 evaluation (without any padding) on LibriSpeech data
- Wav2Vec2 SavedModel evaluation (with constant padding upto 246000 length) on LibriSpeech data
- Small demo of how to use Wav2Vec2 for inference for ASR task
Please visit my webpage:https://thevasudevgupta.com/ to know more about my work.
PinnedLoading
- gsoc-wav2vec2
gsoc-wav2vec2 PublicGSoC'2021 | TensorFlow implementation of Wav2Vec2
- transformers-adapters
transformers-adapters PublicThis repositary hosts my experiments for the project, I did with OffNote Labs.
Something went wrong, please refresh the page to try again.
If the problem persists, check theGitHub status page orcontact support.
If the problem persists, check theGitHub status page orcontact support.