[ICON 2020] TensorFlow Code for "End-to-End Automatic Speech Recognition System for Gujarati"
-
Updated
Jul 26, 2021 - Python
[ICON 2020] TensorFlow Code for "End-to-End Automatic Speech Recognition System for Gujarati"
A from-scratch Transformer for English-to-Chinese translation in a single PyTorch notebook. Follows the original encoder-decoder design with ~7.5M parameters, 15 epochs, and greedy decoding for short sentences. Built for readability as a teaching implementation. MIT licensed.
This project is dedicated to Morse code recognition on different audio signals. It includes analytical and ML methods for signal processing and tone morse signals decoding.
Neural Machine Translation system featuring tokenization, vocabularies, Transformer training, greedy decoding, BLEU evaluation, and CLI inference built entirely from scratch.
Official code for the TMLR 2026 paper on BF16/FP16 divergence in LLM greedy decoding and selective FP32 lm_head recomputation.
Latency, diversity, and quality benchmark for autoregressive decoding strategies on RTX 2070: greedy, top-k, top-p, min-p, and beam search across GPT-2 models.
[SGU] 841448 - NLP (2025-2026 / HK1)
Educational English-to-French Seq2Seq translation model built with PyTorch LSTMs, vocabulary preprocessing, training, validation and greedy decoding.
Turbo LLM: exact (token-identical) Llama 3.2 1B Instruct inference on x86 CPUs in one dependency-free C file. Lossless 12-bit weights, an exact pruned output layer and EAGLE-3 speculative decoding, reading about a third of the memory per token of a bf16 runner.
To associate your repository with the greedy-decoding topic, visit your repo's landing page and select "manage topics."