This repository is the official implementation of the ECAI 2024 conference paper SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
☆69Aug 13, 2024Updated last year
Alternatives and similar repositories for subllm
Users that are interested in subllm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆46Nov 2, 2023Updated 2 years ago
- python wrapper for kaldi's native I/O☆27Jan 9, 2025Updated last year
- Colab notebooks for Next-gen Kaldi☆31Oct 12, 2025Updated 7 months ago
- Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup☆79Jun 30, 2025Updated 11 months ago
- UnitEval is a benchmarking and evaluation tools for AutoDev Coder.☆14Jan 2, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆57Apr 9, 2026Updated 2 months ago
- Python wrapper for kaldi's arpa2fst☆38Aug 27, 2025Updated 9 months ago
- Source code for Consistent ensemble distillation for audio tagging☆70Mar 20, 2026Updated 2 months ago
- ☆28Apr 24, 2026Updated last month
- 🤗 R1-AQA Model: mispeech/r1-aqa☆324Mar 28, 2025Updated last year
- c# library for decoding K2 transducer Models，used in speech recognition (ASR)☆13Aug 20, 2025Updated 9 months ago
- Colab notebook for fine-tuning Qwen2-Audio with trl's SFT and PPO trainers.☆24Nov 23, 2024Updated last year
- Offline Speaker Diarization with SenseVoice by Sherpa ONNX.☆15Dec 23, 2024Updated last year
- ☆41May 12, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- CTC decoder with hotwords for ASR.☆36Apr 13, 2025Updated last year
- A Python interface to OpenFst (fix FstDrawer interface issue for 1.6 version)☆17Apr 2, 2018Updated 8 years ago
- Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-Step High-Fidelity Audio Generation☆144Mar 8, 2026Updated 3 months ago
- ☆41Oct 16, 2025Updated 7 months ago
- Python runtime for WeTextProcessing (does not depend on Pynini)☆52Nov 28, 2025Updated 6 months ago
- [ACL 2026 Main] Open-Ended Speaking Style Modeling via Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training☆83Apr 6, 2026Updated 2 months ago
- A simple command line tool to calculate WER for ASR.☆14Oct 14, 2024Updated last year
- An ASR toolkit with the freedom of topology☆10Dec 18, 2023Updated 2 years ago
- ☆12Oct 17, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆217Sep 10, 2024Updated last year
- RWKV-based Text-to-Speech implementation in Rust☆27Oct 14, 2025Updated 7 months ago
- Apply https://github.com/k2-fsa/sherpa-ncnn in live streaming and WebRTC☆20Apr 16, 2023Updated 3 years ago
- Automatic Speech Recognition at the University of Edinburgh.☆16Mar 14, 2021Updated 5 years ago
- Crowdsourced and Automatic Speech Prominence Estimation☆26Apr 12, 2024Updated 2 years ago
- ☆70Dec 30, 2025Updated 5 months ago
- Building a VLM model starts from the basic module.☆18Apr 7, 2024Updated 2 years ago
- 来自于文章Paraformer-v2: An improved non-autoregressive transformer for noise-robust speech recognition☆29Nov 20, 2024Updated last year
- 天池算法比赛《BetterMixture - 大模型数据混合挑战赛》的第一名top1解决方案☆33Jul 7, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆23Oct 17, 2024Updated last year
- An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement☆193Apr 28, 2026Updated last month
- Automatically exported from code.google.com/p/transducersaurus☆11Apr 1, 2015Updated 11 years ago
- AutoHallusion Codebase (EMNLP 2024)☆23Dec 6, 2024Updated last year
- TTS-Wrapper makes it easier to use text-to-speech APIs by providing a unified and easy-to-use interface.☆20Jul 26, 2024Updated last year
- Simple voice activity detection (VAD) algorithm in Python☆15Aug 10, 2023Updated 2 years ago
- ☆1,420Jun 1, 2026Updated last week