2023

• 7 November 2023 - An Almost Pointless Exercise in GPU Optimization
• 1 November 2023 - Reduce Model Tuning Costs with MuP
• 11 October 2023 - Building a Radio Translation Streaming Service in Python
• 11 September 2023 - Improving Speaker Diarization with Self-supervised Learning
• 4 September 2023 - How to Access Microphones Through the Browser API
• 1 September 2023 - How to Deploy HuggingFace Translation Models on GPU Servers
• 28 April 2023 - Fast and Accurate GPU Quantization for Transformers
• 28 March 2023 - How to Accurately Time CUDA Kernels in Pytorch

2024

• 6 September 2024 - Exploring the trade-off between speed and accuracy in real-time transcription
• 16 March 2024 - Sparse All-Reduce in PyTorch
• 11 January 2024 - The.Shed: Using Speechmatics Capabilities in real-time