hedrergudene
Spanish mathematician. What I really enjoy is developing math tools to solve open problems in Deep Learning.
Credicorp
Pinned Repositories
asr-sd-pipeline
Speech recognition & diarisation solution with text alignment, deployed in AML pipelines
GenImgModels-Baseline
Baseline for image generative models training
hedrergudene
mesinesp2-ner
Entity recognition use case on a Spanish, domain-specific corpus
ml-template-azure
Sample code to deploy fast, scalable tabular ML solutions in Azure Machine Learning
MultiTask_NLU
Multitask NLU architecture for text and token classification tasks.
nerfit
Segmentation_FTYM
Real-time facial semantic segmentation based on Fake It Till You Make It dataset using transformers
ultralytics
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
ZSL_CLIP
hedrergudene's Repositories
hedrergudene/asr-sd-pipeline
Speech recognition & diarisation solution with text alignment, deployed in AML pipelines
hedrergudene/MultiTask_NLU
Multitask NLU architecture for text and token classification tasks.
hedrergudene/GenImgModels-Baseline
Baseline for image generative models training
hedrergudene/nerfit
hedrergudene/ZSL_CLIP
hedrergudene/hedrergudene
hedrergudene/mesinesp2-ner
Entity recognition use case on a Spanish, domain-specific corpus
hedrergudene/ml-template-azure
Sample code to deploy fast, scalable tabular ML solutions in Azure Machine Learning
hedrergudene/Segmentation_FTYM
Real-time facial semantic segmentation based on Fake It Till You Make It dataset using transformers
hedrergudene/ultralytics
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
hedrergudene/NeMo
NeMo: a toolkit for conversational AI
hedrergudene/SCViT
Repository containing implementation of SCViT and experiment tracking
hedrergudene/distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
hedrergudene/faster-whisper
Faster Whisper transcription with CTranslate2
hedrergudene/scikit-optimize
Sequential model-based optimization with a `scipy.optimize` interface
hedrergudene/setfit
Efficient few-shot learning with Sentence Transformers
hedrergudene/whisper-diarization
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper