Jorge Iranzo (jorirsan)

jorirsan

Geek Repo

Company:Universitat Politècnica de València

Location:Valencia

Github PK Tool:Github PK Tool

Jorge Iranzo's starred repositories

Language:PythonLicense:MITStargazers:10Issues:0Issues:0

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Language:Jupyter NotebookStargazers:10750Issues:0Issues:0

RapidFuzz

Rapid fuzzy string matching in Python using various string metrics

Language:C++License:MITStargazers:2506Issues:0Issues:0

jiwer

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

Language:PythonLicense:Apache-2.0Stargazers:576Issues:0Issues:0

outlines

Structured Text Generation

Language:PythonLicense:Apache-2.0Stargazers:7324Issues:0Issues:0

epitran

A tool for transcribing orthographic text as IPA (International Phonetic Alphabet)

Language:PythonLicense:MITStargazers:613Issues:0Issues:0

toLLMatch

toLLMatch🔪: Context-aware LLM-based simultaneous translation

Language:Jupyter NotebookLicense:MITStargazers:3Issues:0Issues:0

simul_whisper

Code for our INTERSPEECH paper Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection

Language:PythonStargazers:11Issues:0Issues:0
License:MITStargazers:2Issues:0Issues:0

ccextractor

CCExtractor - Official version maintained by the core team

Language:CLicense:GPL-2.0Stargazers:689Issues:0Issues:0

whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

Language:PythonLicense:AGPL-3.0Stargazers:1740Issues:0Issues:0

Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

Language:PythonLicense:MITStargazers:2895Issues:0Issues:0

MLVU

🔥🔥MLVU: Multi-task Long Video Understanding Benchmark

Language:PythonStargazers:96Issues:0Issues:0

VideoLLaMA2

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Language:PythonLicense:Apache-2.0Stargazers:571Issues:0Issues:0

NAST-S2x

A fast speech-to-any translation model that supports simultaneous decoding and offers 28× speedup.

Language:PythonStargazers:51Issues:0Issues:0

paella-core

Paella Player core library

Language:JavaScriptLicense:ECL-2.0Stargazers:20Issues:0Issues:0

mbrs

A library for minimum bayes risk (MBR) decoding

Language:PythonLicense:MITStargazers:14Issues:0Issues:0

eole

Open language modeling toolkit based on PyTorch

Language:PythonLicense:MITStargazers:26Issues:0Issues:0

eamt24-linguistic-mt

A repo for resources for our EAMT 2024 tutorial

Stargazers:6Issues:0Issues:0

llm-foundry

LLM training code for Databricks foundation models

Language:PythonLicense:Apache-2.0Stargazers:3885Issues:0Issues:0
Language:PythonStargazers:1Issues:0Issues:0

CroCoAlign

A Cross-Lingual, Context-Aware and Fully-Neural Sentence Alignment System for Long Texts.

Language:PythonLicense:NOASSERTIONStargazers:6Issues:0Issues:0

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Language:PythonLicense:Apache-2.0Stargazers:6729Issues:0Issues:0

apptainer

Apptainer: Application containers for Linux

Language:GoLicense:NOASSERTIONStargazers:1001Issues:0Issues:0

compare-mt

A tool for holistic analysis of language generations systems

Language:PythonLicense:BSD-3-ClauseStargazers:466Issues:0Issues:0

lingua-py

The most accurate natural language detection library for Python, suitable for short text and mixed-language text

Language:PythonLicense:Apache-2.0Stargazers:1035Issues:0Issues:0

tensorrt_backend

The Triton backend for TensorRT.

Language:C++License:BSD-3-ClauseStargazers:58Issues:0Issues:0

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

Language:PythonLicense:MITStargazers:3296Issues:0Issues:0

konoha

🌿 An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.

Language:PythonLicense:MITStargazers:224Issues:0Issues:0