Skip to content

@mesolitica Mesolitica

Change the repository type filter

All

    Repositories list

    45 repositories

    • malaysian-dataset

      Public
      We gather Malaysian dataset! https://malaysian-dataset.readthedocs.io/
      text-miningcorpusmalaysiabahasa-melayumanglishmalay-dataset
      Jupyter Notebook
      •
      Apache License 2.0
      •111•312•5•2•Updated Mar 25, 2025Mar 25, 2025

    • malaya-speech

      Public
      Speech Toolkit for Malaysian language, https://malaya-speech.readthedocs.io/
      Jupyter Notebook
      •
      MIT License
      •43•249•5•0•Updated Mar 24, 2025Mar 24, 2025

    • malaya

      Public
      Natural Language Toolkit for Malaysian language, https://malaya.readthedocs.io/
      natural-language-processingsentiment-analysistensorflowlanguage-detectionentity-frameworknormalizerneremotion-analysispos-taggingmalay
      Jupyter Notebook
      •
      MIT License
      •127•483•3•2•Updated Mar 24, 2025Mar 24, 2025

    • Chunk-loss-LoRA

      Public
      Fused kernel chunk loss to include LoRA to reduce memory, support DeepSpeed ZeRO3.
      Python
      •1•1•2•0•Updated Mar 22, 2025Mar 22, 2025

    • initial-paged-flash-attention

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •28k•1•0•0•Updated Mar 15, 2025Mar 15, 2025

    • transformers-openai-api

      Public
      Lightweight continuous batching OpenAI compatibility using HuggingFace Transformers include T5 and Whisper.
      Python
      •3•20•4•0•Updated Mar 15, 2025Mar 15, 2025

    • accelerate-torch-compile-speechlm

      Public
      🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
      Python
      •
      Apache License 2.0
      •1.1k•0•0•0•Updated Feb 26, 2025Feb 26, 2025

    • dynamic-batch-TTS-pipeline

      Public
      Dynamic batching for Speech Enhancement, Speech Tokenizer and TTS.
      Jupyter Notebook
      •2•8•0•0•Updated Feb 18, 2025Feb 18, 2025

    • picotron-zero1

      Public
      Minimalistic 4D-parallelism distributed training framework for education purpose
      Python
      •
      Apache License 2.0
      •73•0•0•0•Updated Feb 17, 2025Feb 17, 2025

    • context-parallelism

      Public
      Context Parallelism, support Ring Attention and Tree Attention.
      Jupyter Notebook
      •4•4•2•0•Updated Feb 9, 2025Feb 9, 2025

    • ml-cross-entropy-lora-lm-head

      Public
      CCE for LoRA LM Head
      Python
      •
      Other
      •33•0•0•0•Updated Feb 5, 2025Feb 5, 2025

    • MeloTTS-MS

      Public
      High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese, Korean and Malay.
      Python
      •
      MIT License
      •779•2•0•0•Updated Feb 5, 2025Feb 5, 2025

    • StyleTTS2-MS

      Public
      StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
      Python
      •
      MIT License
      •519•2•0•0•Updated Feb 5, 2025Feb 5, 2025

    • async-parler-tts

      Public
      Inference and training library for high-quality TTS models.
      Python
      •
      Apache License 2.0
      •545•1•0•0•Updated Feb 3, 2025Feb 3, 2025

    • memory-efficient-grpo

      Public
      Train transformer language models with reinforcement learning.
      Python
      •
      Apache License 2.0
      •1.7k•4•0•0•Updated Feb 2, 2025Feb 2, 2025

    • AuxiliaryASR-Phonemizer

      Public
      Joint CTC-S2S Phoneme-level ASR for Voice Conversion and TTS (Text-Mel Alignment)
      Python
      •
      MIT License
      •40•1•0•0•Updated Jan 25, 2025Jan 25, 2025

    • PL-BERT-MS

      Public
      Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions
      Python
      •
      MIT License
      •49•0•0•0•Updated Jan 23, 2025Jan 23, 2025

    • cookbook

      Public
      cookbooks 📖 for Mesolitica products!
      Jupyter Notebook
      •
      MIT License
      •1•6•0•0•Updated Jan 20, 2025Jan 20, 2025

    • F5-TTS

      Public
      Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
      Python
      •
      MIT License
      •1.5k•1•0•0•Updated Jan 17, 2025Jan 17, 2025

    • qwen2audio-multipack

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •28k•1•0•0•Updated Jan 14, 2025Jan 14, 2025

    • llama-flex-attention-multipack

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •28k•0•0•0•Updated Dec 13, 2024Dec 13, 2024

    • vocos

      Public
      Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
      Python
      •
      MIT License
      •108•0•0•0•Updated Dec 13, 2024Dec 13, 2024

    • ml-cross-entropy-whisper

      Public
      CCE for Whisper
      Python
      •
      Other
      •33•1•0•0•Updated Dec 11, 2024Dec 11, 2024

    • nous-chat-widget

      Public
      Vue
      •3•6•0•0•Updated Dec 4, 2024Dec 4, 2024

    • t5-sdpa-multipack

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •28k•2•0•0•Updated Nov 25, 2024Nov 25, 2024

    • dynamic-batch-RAG-pipeline

      Public
      Dynamic batching for Document Layout and OCR, suitable for RAG, with extra tools.
      Jupyter Notebook
      •1•11•0•0•Updated Nov 25, 2024Nov 25, 2024

    • fish-speech

      Public
      Brand new TTS solution
      Python
      •
      Other
      •1.6k•0•0•0•Updated Nov 18, 2024Nov 18, 2024

    • research-paper

      Public
      Preprint under Mesolitica.
      TeX
      •1•1•0•0•Updated Sep 2, 2024Sep 2, 2024

    • chat-widget

      Public
      Customizable Web Chat Widget 💬
      JavaScript
      •0•0•0•0•Updated Aug 25, 2024Aug 25, 2024

    • vllm-context-parallelism

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      •
      Apache License 2.0
      •6.5k•2•0•0•Updated Aug 17, 2024Aug 17, 2024