Search Results for "stage" - Page 3
Sort By:
Showing 72 open source projects for "stage"
View related business solutions-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
1
MARS5
MARS5 speech model (TTS) from CAMB.AI
MARS5-TTS is CAMB.AI’s open-source English speech model designed for high-quality text-to-speech and voice emulation. It uses a two-stage architecture that combines an autoregressive (AR) model with a non-autoregressive (NAR) model, giving it both expressiveness and speed. The model is built to handle prosodically challenging content such as sports commentary, anime dialogue, and other high-energy or highly varied speech patterns with realistic rhythm and intonation. -
2
minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm
...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. -
3
SalesGPT
Context-aware AI Sales Agent to automate sales outreach
This repo is an implementation of a context-aware AI Agent for Sales using LLMs and can work across voice, email and texting (SMS, WhatsApp, WeChat, Weibo, Telegram, etc.). SalesGPT is context-aware, which means it can understand what stage of a sales conversation it is in and act accordingly. Moreover, SalesGPT has access to tools, such as your own pre-defined product knowledge base, significantly reducing hallucinations. -
4
StyleTTS 2
Towards Human-Level Text-to-Speech through Style Diffusion
...It extends the original StyleTTS idea by introducing a style diffusion model that can sample rich, realistic speaking styles conditioned on reference speech, allowing highly expressive and diverse prosody. The architecture uses a two-stage training process and leverages an auxiliary speech language model to guide generation toward more natural and coherent utterances. StyleTTS2 supports both single-speaker and multi-speaker configurations, with the ability to sample or transfer styles from reference audio, making it powerful for expressive TTS and character voices. ... -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
Shap-E
Generate 3D objects conditioned on text or images
The shap-e repository provides the official code and model release for Shap-E, a conditional generative model designed to produce 3D assets (implicit functions, meshes, neural radiance fields) from text or image prompts. The model is built with a two-stage architecture: first an encoder that maps existing 3D assets into parameterizations of implicit functions, and then a conditional diffusion model trained on those parameterizations to generate new assets. Because it works at the level of implicit functions, Shap-E can render output both as textured meshes and NeRF-style volumetric renderings. ... -
6
PIFuHD
High-Resolution 3D Human Digitization from A Single Image
...The method operates by learning an implicit occupancy / surface function conditioned on the image and camera projection; at inference time it queries dense points to reconstruct a mesh via marching cubes. It also uses a two-stage architecture: a coarse global model followed by local refinement patches to capture fine detail, balancing global consistency and local detail. The repo includes training pipelines, dataset loaders (for Multi-POP, etc.), and inference scripts for mesh output including depth maps for postprocessing. To help practical use, there are utilities for normal estimation, texture back-projection, mesh cleanup, and integration with rendering pipelines. -
7
VALL-E
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
...Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that VALL-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. ... -
8
NanoDet-Plus
Lightweight anchor-free object detection model
Super fast and high accuracy lightweight anchor-free object detection model. Real-time on mobile devices. NanoDet is a FCOS-style one-stage anchor-free object detection model which using Generalized Focal Loss as classification and regression loss. In NanoDet-Plus, we propose a novel label assignment strategy with a simple assign guidance module (AGM) and a dynamic soft label assigner (DSLA) to solve the optimal label assignment problem in lightweight model training. -
9
Point-E
Point cloud diffusion for 3D model synthesis
...Its principal advantage is speed: it can generate 3D assets in just 1–2 minutes on a single GPU, which is significantly faster than many competing text-to-3D models. The model works via a two-stage diffusion approach: first, it uses a text → image diffusion network to produce a synthetic 2D view consistent with the prompt; then a second diffusion model converts that image into a 3D point cloud. While it does not match the fine detail of some slower methods, the tradeoff in speed makes it practical for prototyping and interactive 3D generation. ... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
10
Compose
A machine learning tool for automated prediction engineering
Compose is a machine learning tool for automated prediction engineering. It allows you to structure prediction problems and generate labels for supervised learning. An end user defines an outcome of interest by writing a labeling function, then runs a search to automatically extract training examples from historical data. Its result is then provided to Featuretools for automated feature engineering and subsequently to EvalML for automated machine learning. Prediction problems are structured... -
11
VoiceSmith
[WIP] VoiceSmith makes training text to speech models easy
...This is untested since I don't currently own a Mac. NVIDIA GPU with CUDA support is highly recommended, you can train on CPU otherwise but it will take days if not weeks. VoiceSmith currently uses a two-stage modified DelightfulTTS and UnivNet pipeline. -
12
CIPS-3D
3D-aware GANs based on NeRF (arXiv)
...The problem of mirror symmetry refers to the sudden change of the direction of the bangs near the yaw angle of pi/2. We propose to use an auxiliary discriminator to solve this problem. Note that in the initial stage of training, the auxiliary discriminator must dominate the generator more than the main discriminator does. Otherwise, if the main discriminator dominates the generator, the mirror symmetry problem will still occur. In practice, progressive training is able to guarantee this. We have trained many times from scratch. Adding an auxiliary discriminator stably solves the mirror symmetry problem. -
13
VoiceFixer
General Speech Restoration
VoiceFixer is a machine-learning framework for “speech restoration”: given a degraded or distorted audio recording — with noise, clipping, low sampling rate, reverberation, or other artifacts — it attempts to recover high-fidelity, clean speech. The architecture works in two stages: first an analysis stage that tries to extract “clean” intermediate features from the noisy audio (e.g. removing noise, denoising, dereverberation, upsampling), and then a neural vocoder-based synthesis stage that reconstructs a high-quality waveform from those features. Unlike many single-purpose noise reduction tools, VoiceFixer targets a “general speech restoration” problem (GSR), capable of handling multiple types of distortions at once, which makes it suitable for old recordings, phone-call audio, amateur voice recordings, or archival media. ... -
14
Tez
Tez is a super-simple and lightweight Trainer for PyTorch
...It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch. tez (तेज़ / تیز) means sharp, fast & active. This is a simple, to-the-point, library to make your PyTorch training easy. This library is in early-stage currently! So, there might be breaking changes. Currently, tez supports cpu, single gpu and multi-gpu & tpu training. More coming soon! Using tez is super-easy. We don't want you to be far away from pytorch. So, you do everything on your own and just use tez to make a few things simpler. -
15
VITS
Conditional Variational Autoencoder with Adversarial Learning
VITS is a foundational research implementation of “VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech,” a well-known neural TTS architecture. Unlike traditional two-stage systems that separately train an acoustic model and a vocoder, VITS trains an end-to-end model that maps text directly to waveform using a conditional variational autoencoder combined with normalizing flows and adversarial training. This architecture enables parallel generation (fast inference) while achieving speech quality that rivals or surpasses many two-stage systems. ... -
16
YOLOv4-large
Scaled-YOLOv4: Scaling Cross Stage Partial Network
YOLOv4-large is an open-source implementation of the Scaled-YOLOv4 object detection architecture, designed to improve both the accuracy and scalability of real-time computer vision models. The project provides a PyTorch implementation of the Scaled-YOLOv4 framework, which extends the original YOLOv4 architecture using Cross Stage Partial (CSP) networks and new scaling techniques. Unlike earlier object detection systems that only scale depth or width, this architecture scales multiple aspects of the neural network including structure, resolution, and channel configuration. This scaling strategy enables the model to adapt to different hardware environments while maintaining a strong balance between speed and detection accuracy. ... -
17
DrQA
Reading Wikipedia to Answer Open-Domain Questions
DrQA is an open-domain question answering system that reads large text corpora—famously Wikipedia—to answer natural language questions with extractive spans. It follows a two-stage pipeline: a fast document retriever first narrows down candidate articles, and a neural machine reader then predicts the exact answer span from those passages. The retriever relies on classic IR features (like TF-IDF and n-gram statistics) to remain lightweight and scalable to millions of documents. The reader is a neural model trained on supervised QA data to estimate start and end positions within a paragraph, and it can be adapted to new domains through fine-tuning or distant supervision. ... -
18
onnxt5
Summarization, translation, sentiment-analysis, text-generation, etc.
Summarization, translation, sentiment analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX. This package is still in the alpha stage, therefore some functionalities such as beam searches are still in development. The simplest way to get started for generation is to use the default pre-trained version of T5 on ONNX included in the package. Please note that the first time you call get_encoder_decoder_tokenizer, the models are being downloaded which might take a minute or two. ... -
19
The Player Project: Player is a networked interface to robots and sensors. Stage and Gazebo are Player-friendly multiple-robot simulators. The software aims for POSIX compliance and runs on most UNIX-like OS's. Some parts also work on Windows.
-
20
DC-TTS
TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DC-TTS is a TensorFlow implementation of the DC-TTS architecture, a fully convolutional text-to-speech system designed to be efficiently trainable while producing natural speech. It follows the “Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention” paper, but the author adapts and extends the design to make it practical for real experiments. The model is split into two networks: Text2Mel, which maps text to mel-spectrograms, and SSRN... -
21
EducationalLCS
eLCS - Educational Learning Classifier System
Educational Learning Classifier System (eLCS) is a set of learning classifier system (LCS) educational demos designed to introduce students or researchers to the basics of a modern Michigan-style LCS algorithm. This eLCS package includes 5 different implementations of a basic LCS algorithm, as part of a 6 stage set of demos that will be paired with the first introductory LCS textbook. Each eLCS implementations (from demo 2 up to demo 6) progressively add major components of the entire LCS algorithm in order to illustrate how work, how they are coded, and what impact they have on how an LCS algorithm runs. The Demo 6 version of eLCS is most similar to the UCS algorithm. ... -
22
PyCBR
This project aims to provide a simple python interface for CBR
...Python is one of the most to used languages that is becoming popular in every community for its simplicity & ease of learning. It has an interface for wordnet (through nltk tools) which brings us why pyCBR exists. This script is still in its infant stage of CBR & script matching. Nontheless you could use it to do many crazy stuff. Enjoy!!!
