#
kadirnar
Follow
Lists (10)
Starred repositories
Building LLMs from scratch following the book from S. Raschka
The implementation for "Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions"
Bu Course LLM(Large Language Model) Fine Tune işlemlerini Türkçe klavuz olarak
Trained a Whisper model a ~30M (whisper tiny.en) architecture I coded from ground up to build a small ASR model, going through the below-mentioned stage from scratch. Trained on GigaSpeech dataset …
[NAACL 2025] WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching
Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.
Fast and accurate automatic speech recognition (ASR) for edge devices
AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
llama3 implementation one matrix multiplication at a time
Pytorch implementation of "CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR".
Audio generation using diffusion models, in PyTorch.
[EMNLP 2024] ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers
The repository of Typhoon2-Audio, Thai audio-language model that supports speech-in and speech-out
The Vokan Architecture (Tsukasa speech based)
A lightweight StyleTTS2 and Vokan inference library
[ICASSP 2025] Official Pytorch implementation of "Large Language Models are Strong Audio-Visual Speech Recognition Learners".
Awesome Speech Dataset, including download links and a brief explanation for each resource. These datasets provide diverse and high-quality speech data covering various domains such as conversation…
8
Updated Mar 13, 2025
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
A collection of all our phonemeizers for dataset construction and inference
a Frontier Japanese Speech Generation net
A repository to unravel the language of GPUs, making their kernel conversations easy to understand