Search Results for "tokenizer"
Sort By:
Showing 70 open source projects for "tokenizer"
View related business solutions-
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
Tokenizer
A small library for converting tokenized PHP source code into XML
A small library for converting tokenized PHP source code into XML. You can add this library as a local, per-project dependency to your project using Composer. If you only need this library during development, for instance to run your project's test suite, then you should add it as a development-time dependency. -
2
SentencePiece
Unsupervised text tokenizer for Neural Network-based text generation
SentencePiece is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training. SentencePiece implements subword units (e.g., byte-pair-encoding (BPE) [Sennrich et al.]) and unigram language model [Kudo.]) with the extension of direct training from raw sentences. -
3
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
tiktoken is a high-performance, tokenizer library (based on byte-pair encoding, BPE) designed for use with OpenAI’s models. It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). -
4
minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm
...It operates on UTF-8 encoded bytes rather than Unicode characters, which makes it robust to arbitrary text inputs and avoids needing a language-specific character vocabulary. The repository is structured as a teaching-oriented implementation that shows how to train a tokenizer by learning merge rules, then apply those merges to encode text into token IDs and decode tokens back into text. It is intentionally small and readable so developers can understand each stage of BPE, including the mechanics of pair counting, merge application, and vocabulary growth. The project is especially useful for practitioners who want to demystify how LLM tokenizers work or who need a lightweight reference implementation for experimentation. -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
5
VoxCPM2
Tokenizer-Free TTS for Multilingual Speech Generation
VoxCPM2 is an advanced open-source text-to-speech system that redefines speech synthesis by eliminating traditional tokenization and instead generating continuous speech representations through a diffusion-based autoregressive architecture. Built on top of the MiniCPM model family, it enables highly natural, expressive, and context-aware speech generation that adapts tone, emotion, and pacing directly from input text. The system is trained on massive multilingual datasets, enabling support... -
6
VoxCPM
TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
VoxCPM is a tokenizer-free text-to-speech system that models speech in a continuous space, aiming for extremely realistic, context-aware synthesis and true-to-life zero-shot voice cloning. Instead of converting speech into discrete tokens, it uses an end-to-end diffusion-autoregressive architecture built on the MiniCPM-4 backbone, combining hierarchical language modeling, finite scalar quantization (FSQ), and local Diffusion Transformers. -
7
1D Visual Tokenization and Generation
This repo contains the code for 1D tokenizer and generator
The 1D Visual Tokenization and Generation project from ByteDance introduces a novel “one-dimensional” tokenizer designed for images: instead of representing images with large grids of 2D tokens (as in many prior generative/image-modeling systems), it compresses images into as few as 32 discrete tokens (or more, optionally) — thereby achieving a very compact, efficient representation that drastically speeds up generation and reconstruction while retaining strong fidelity. -
8
FireRedTTS-2
Long-form streaming TTS system for multi-speaker dialogue generation
FireRedTTS2 is a next-generation open-source text-to-speech (TTS) system focused on long-form, streaming speech synthesis for multi-speaker dialogue, delivering stable natural speech with context-aware prosody and reliable speaker transitions that support real-time and conversational applications. It features a specialized streaming speech tokenizer and a dual-transformer architecture that enables low latency and high-quality synthesis, making it suitable for interactive systems like chatbots, podcasts, and applications where dynamic turn-taking between speakers is essential. FireRedTTS2 supports multilingual output and speaker flexibility, enabling scenarios that involve language switching, cross-lingual voice cloning, and expressive dialogue generation that maintains consistency over longer utterances. -
9
ZhParser
PostgreSQL extension for full-text search of Chinese language
zhparser is a PostgreSQL extension for full-text search of Chinese text. It integrates with PostgreSQL's text search engine to tokenize Chinese characters using a dictionary-based segmentation algorithm. zhparser is a valuable tool for improving search accuracy and performance in Chinese-language applications. -
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
10
gTTS
Python library and CLI tool to interface with Google Translate
...It lets you send text to the Google Translate TTS endpoint and receive spoken audio back as MP3 data, either written to a file, a file-like object, or standard output. The library is designed to handle long texts, using a speech-specific sentence tokenizer that keeps intonation and punctuation natural while splitting requests into acceptable chunks. It supports customizable text pre-processors, which can correct pronunciations, tweak formatting, or handle domain-specific vocabulary before sending it to the API. gTTS is primarily aimed at developers who want a quick way to add cloud-backed speech to scripts, apps, or pipelines without managing any model weights locally. ... -
11
nanochat
The best ChatGPT that $100 can buy
nanochat is a from-scratch, end-to-end “mini ChatGPT” that shows the entire path from raw text to a chatty web app in one small, dependency-lean codebase. The repository stitches together every stage of the lifecycle: tokenizer training, pretraining a Transformer on a large web corpus, mid-training on dialogue and multiple-choice tasks, supervised fine-tuning, optional reinforcement learning for alignment, and finally efficient inference with caching. Its north star is approachability and speed: you can boot a fresh GPU box and drive the whole pipeline via a single script, producing a usable chat model in hours and a clear markdown report of what happened. ... -
12
Step-Audio-EditX
LLM-based Reinforcement Learning audio edit model
...Rather than treating audio editing as low-level waveform manipulation, this model converts speech into a sequence of discrete “audio tokens” (via a dual-codebook tokenizer) — combining a linguistic token stream and a semantic (prosody/emotion/style) token stream — thereby abstracting audio editing into high-level token operations. This allows users to modify not only what is said (the text) but also how it's said: emotion, tone, speaking style, prosody, accent, even paralinguistic cues. Because the model is trained with a “large-margin learning” objective over many synthesized and natural speech samples, it gains robust control over expressive attributes, and can perform iterative editing: e.g. you could record a line, then ask the model to “make it sadder,” “speak slower,” or “change accent to X.” -
13
Kronos
A Foundation Model for the Language of Financial Markets
Kronos is a specialized open-source foundation model designed for analyzing and predicting financial market data using time-series representations of candlestick patterns. It is built as a decoder-only Transformer model trained specifically on K-line data, which captures open, high, low, close, and volume information across multiple global exchanges. The system introduces a novel tokenization approach that converts continuous financial data into discrete tokens, enabling the model to process... -
14
Happy-LLM
Large Language Model Principles and Practice Tutorial from Scratch
...It explains the Transformer architecture, pre-training paradigms, and model scaling strategies while also providing hands-on coding examples so readers can implement and experiment with their own models. The tutorial emphasizes practical understanding by walking users through building and training small language models, including tokenizer construction, pre-training workflows, and fine-tuning methods. -
15
AudioCraft
Audiocraft is a library for audio processing and generation
...It includes MusicGen for music generation conditioned on text (and optionally melody) and AudioGen for text-conditioned sound effects and environmental audio. Both models operate over discrete audio tokens produced by a neural codec (EnCodec), which acts like a tokenizer for waveforms and enables efficient sequence modeling. The repo provides inference scripts, checkpoints, and simple Python APIs so you can generate clips from prompts or incorporate the models into applications. It also contains training code and recipes, so researchers can fine-tune on custom data or explore new objectives without building infrastructure from scratch. ... -
16
Bumblebee
Pre-trained Neural Network models in Axon
Bumblebee provides pre-trained Neural Network models on top of Axon. It includes integration with Models, allowing anyone to download and perform Machine Learning tasks with few lines of code. The best way to get started with Bumblebee is with Livebook. Our announcement video shows how to use Livebook's Smart Cells to perform different Neural Network tasks with a few clicks. You can then tweak the code and deploy it. First, add Bumblebee and EXLA as dependencies in your mix.exs. EXLA is an... -
17
Qwen3-Coder
Qwen3-Coder is the code version of Qwen3
Qwen3-Coder is the latest and most powerful agentic code model developed by the Qwen team at Alibaba Cloud. Its flagship version, Qwen3-Coder-480B-A35B-Instruct, features a massive 480 billion-parameter Mixture-of-Experts architecture with 35 billion active parameters, delivering top-tier performance on coding and agentic tasks. This model sets new state-of-the-art benchmarks among open models for agentic coding, browser-use, and tool-use, matching performance comparable to leading models... -
18
Gemma in PyTorch
The official PyTorch implementation of Google's Gemma models
...It includes model definitions, configuration files, and loading utilities for multiple parameter scales, enabling quick evaluation and downstream adaptation. The repository demonstrates text generation pipelines, tokenizer setup, quantization paths, and adapters for low-rank or parameter-efficient fine-tuning. Example notebooks walk through instruction tuning and evaluation so teams can benchmark and iterate rapidly. The code is organized to be legible and hackable, exposing attention blocks, positional encodings, and head configurations. With standard PyTorch abstractions, it integrates easily into existing training loops, loggers, and evaluation harnesses. -
19
LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
LLMs-from-scratch is an educational codebase that walks through implementing modern large-language-model components step by step. It emphasizes building blocks—tokenization, embeddings, attention, feed-forward layers, normalization, and training loops—so learners understand not just how to use a model but how it works internally. The repository favors clear Python and NumPy or PyTorch implementations that can be run and modified without heavyweight frameworks obscuring the logic. Chapters... -
20
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. The design tackles long-standing... -
21
torchtext
Data loaders and abstractions for text and NLP
...Please refer to pytorch.org for the details of PyTorch installation. LTS versions are distributed through a different channel than the other versioned releases. Alternatively, you might want to use the Moses tokenizer port in SacreMoses (split from NLTK). You have to install SacreMoses. To build torchtext from source, you need git, CMake and C++11 compiler such as g++. When building from source, make sure that you have the same C++ compiler as the one used to build PyTorch. A simple way is to build PyTorch from source and use the same environment to build torchtext. ... -
22
-
23
IK Analysis for Elasticsearch
A plugin that integrates Lucene IK analyzer into elasticsearch
...Starting from version 3.0, IK has developed into a common word segmentation component for Java, independent of the Lucene project, and at the same time provides a default optimized implementation of Lucene. In the 2012 version, IK implemented a simple word segmentation ambiguity elimination algorithm, marking the evolution of the IK tokenizer from pure dictionary word segmentation to analog semantic word segmentation. -
24
GPT-2
Code for the paper Language Models are Unsupervised Multitask Learners
This repository contains the code and model weights for GPT-2, a large-scale unsupervised language model described in the OpenAI paper “Language Models are Unsupervised Multitask Learners.” The intent is to provide a starting point for researchers and engineers to experiment with GPT-2: generate text, fine‐tune on custom datasets, explore model behavior, or study its internal phenomena. The repository includes scripts for sampling, training, downloading pre-trained models, and utilities for... -
25
RE/flex lexical analyzer generator
The regex-centric, fast lexical analyzer generator for C++
A C++ high-performance regex library and Flex-compatible lexical analyzer generator with full Unicode support, new indentation anchors, lazy quantifiers, and many other modern features. Accepts Flex lexer specification syntax and is compatible with Bison/Yacc parsers. Generates reusable source code that is easy to understand. Supports fast scanning of UTF-8/16/32 files, strings, and streams. The reflex scanner generator generates clean C++ lexer class code that is thread-safe. Generates...
