PyTorchKR Papers

최신 논문

총 716편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2306.16688공식 코드 · Papers with Code

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores

The ever-growing complexity of reinforcement learning (RL) tasks demands a distributed system to efficiently generate and process a massive amount of data. However, existing open-source libraries suffer from various limitations, which impede their practical use in challenging scenarios where large-scale training is necessary. In this paper, we present a novel abstraction on the dataflows of RL training, which unifies diverse RL training applications into a general framework. Following this abstraction, we develop a scalable, efficient, and extensible distributed RL system called ReaLlyScalableRL, which allows efficient and massively parallelized training and easy development of customized algorithms. Our evaluation shows that SRL outperforms existing academic libraries, reaching at most 21x higher training throughput in a distributed setting. On learning performance, beyond performing and scaling well on common RL benchmarks with different RL algorithms, SRL can reproduce the same solution in the challenging hide-and-seek environment as reported by OpenAI with up to 5x speedup in wall-clock time. Notably, SRL is the first in the academic community to perform RL experiments at a large scale with over 15k CPU cores. SRL source code is available at: https://github.com/openpsi-project/srl .

arXiv:2306.15685공식 코드 · Papers with Code

Implementing contextual biasing in GPU decoder for online ASR

GPU decoding significantly accelerates the output of ASR predictions. While GPUs are already being used for online ASR decoding, post-processing and rescoring on GPUs have not been properly investigated yet. Rescoring with available contextual information can considerably improve ASR predictions. Previous studies have proven the viability of lattice rescoring in decoding and biasing language model (LM) weights in offline and online CPU scenarios. In real-time GPU decoding, partial recognition hypotheses are produced without lattice generation, which makes the implementation of biasing more complex. The paper proposes and describes an approach to integrate contextual biasing in real-time GPU decoding while exploiting the standard Kaldi GPU decoder. Besides the biasing of partial ASR predictions, our approach also permits dynamic context switching allowing a flexible rescoring per each speech segment directly on GPU. The code is publicly released and tested with open-sourced test sets.

arXiv:2306.16384공식 코드 · Papers with Code

Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses

Graph Neural Networks (GNNs) are emerging as a powerful tool for learning from graph-structured data and performing sophisticated inference tasks in various application domains. Although GNNs have been shown to be effective on modest-sized graphs, training them on large-scale graphs remains a significant challenge due to lack of efficient data access and data movement methods. Existing frameworks for training GNNs use CPUs for graph sampling and feature aggregation, while the training and updating of model weights are executed on GPUs. However, our in-depth profiling shows the CPUs cannot achieve the throughput required to saturate GNN model training throughput, causing gross under-utilization of expensive GPU resources. Furthermore, when the graph and its embeddings do not fit in the CPU memory, the overhead introduced by the operating system, say for handling page-faults, comes in the critical path of execution. To address these issues, we propose the GPU Initiated Direct Storage Access (GIDS) dataloader, to enable GPU-oriented GNN training for large-scale graphs while efficiently utilizing all hardware resources, such as CPU memory, storage, and GPU memory with a hybrid data placement strategy. By enabling GPU threads to fetch feature vectors directly from storage, GIDS dataloader solves the memory capacity problem for GPU-oriented GNN training. Moreover, GIDS dataloader leverages GPU parallelism to tolerate storage latency and eliminates expensive page-fault overhead. Doing so enables us to design novel optimizations for exploiting locality and increasing effective bandwidth for GNN training. Our evaluation using a single GPU on terabyte-scale GNN datasets shows that GIDS dataloader accelerates the overall DGL GNN training pipeline by up to 392X when compared to the current, state-of-the-art DGL dataloader.

arXiv:2306.13835공식 코드 · Papers with Code

Computron: Serving Distributed Deep Learning Models with Model Parallel Swapping

Many of the most performant deep learning models today in fields like language and image understanding are fine-tuned models that contain billions of parameters. In anticipation of workloads that involve serving many of such large models to handle different tasks, we develop Computron, a system that uses memory swapping to serve multiple distributed models on a shared GPU cluster. Computron implements a model parallel swapping design that takes advantage of the aggregate CPU-GPU link bandwidth of a cluster to speed up model parameter transfers. This design makes swapping large models feasible and can improve resource utilization. We demonstrate that Computron successfully parallelizes model swapping on multiple GPUs, and we test it on randomized workloads to show how it can tolerate real world variability factors like burstiness and skewed request rates. Computron's source code is available at https://github.com/dlzou/computron.

arXiv:2306.14289공식 코드 · Papers with Code

Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need to be run on resource-constraint edge devices, like mobile phones. In this work, we aim to make SAM mobile-friendly by replacing the heavyweight image encoder with a lightweight one. A naive way to train such a new SAM as in the original SAM paper leads to unsatisfactory performance, especially when limited training sources are available. We find that this is mainly caused by the coupled optimization of the image encoder and mask decoder, motivated by which we propose decoupled distillation. Concretely, we distill the knowledge from the heavy image encoder (ViT-H in the original SAM) to a lightweight image encoder, which can be automatically compatible with the mask decoder in the original SAM. The training can be completed on a single GPU within less than one day, and the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM. For inference speed, With a single GPU, MobileSAM runs around 10ms per image: 8ms on the image encoder and 4ms on the mask decoder. With superior performance, our MobileSAM is around 5 times faster than the concurrent FastSAM and 7 times smaller, making it more suitable for mobile applications. Moreover, we show that MobileSAM can run relatively smoothly on CPU. The code for our project is provided at \href{https://github.com/ChaoningZhang/MobileSAM}{\textcolor{red}{MobileSAM}}), with a demo showing that MobileSAM can run relatively smoothly on CPU.

arXiv:2306.12456공식 코드 · Papers with Code

Pushing the Limits of Machine Design: Automated CPU Design with AI

Design activity -- constructing an artifact description satisfying given goals and constraints -- distinguishes humanity from other animals and traditional machines, and endowing machines with design abilities at the human level or beyond has been a long-term pursuit. Though machines have already demonstrated their abilities in designing new materials, proteins, and computer programs with advanced artificial intelligence (AI) techniques, the search space for designing such objects is relatively small, and thus, "Can machines design like humans?" remains an open question. To explore the boundary of machine design, here we present a new AI approach to automatically design a central processing unit (CPU), the brain of a computer, and one of the world's most intricate devices humanity have ever designed. This approach generates the circuit logic, which is represented by a graph structure called Binary Speculation Diagram (BSD), of the CPU design from only external input-output observations instead of formal program code. During the generation of BSD, Monte Carlo-based expansion and the distance of Boolean functions are used to guarantee accuracy and efficiency, respectively. By efficiently exploring a search space of unprecedented size 10^{10^{540}}, which is the largest one of all machine-designed objects to our best knowledge, and thus pushing the limits of machine design, our approach generates an industrial-scale RISC-V CPU within only 5 hours. The taped-out CPU successfully runs the Linux operating system and performs comparably against the human-designed Intel 80486SX CPU. In addition to learning the world's first CPU only from input-output observations, which may reform the semiconductor industry by significantly reducing the design cycle, our approach even autonomously discovers human knowledge of the von Neumann architecture.

arXiv:2306.11182공식 코드 · Papers with Code

Co-design Hardware and Algorithm for Vector Search

Vector search has emerged as the foundation for large-scale information retrieval and machine learning systems, with search engines like Google and Bing processing tens of thousands of queries per second on petabyte-scale document datasets by evaluating vector similarities between encoded query texts and web documents. As performance demands for vector search systems surge, accelerated hardware offers a promising solution in the post-Moore's Law era. We introduce \textit{FANNS}, an end-to-end and scalable vector search framework on FPGAs. Given a user-provided recall requirement on a dataset and a hardware resource budget, \textit{FANNS} automatically co-designs hardware and algorithm, subsequently generating the corresponding accelerator. The framework also supports scale-out by incorporating a hardware TCP/IP stack in the accelerator. \textit{FANNS} attains up to 23.0$\times$ and 37.2$\times$ speedup compared to FPGA and CPU baselines, respectively, and demonstrates superior scalability to GPUs, achieving 5.5$\times$ and 7.6$\times$ speedup in median and 95\textsuperscript{th} percentile (P95) latency within an eight-accelerator configuration. The remarkable performance of \textit{FANNS} lays a robust groundwork for future FPGA integration in data centers and AI supercomputers.

arXiv:2306.11248공식 코드 · Papers with Code

Dynamic Perceiver for Efficient Visual Recognition

Early exiting has become a promising approach to improving the inference efficiency of deep networks. By structuring models with multiple classifiers (exits), predictions for ``easy'' samples can be generated at earlier exits, negating the need for executing deeper layers. Current multi-exit networks typically implement linear classifiers at intermediate layers, compelling low-level features to encapsulate high-level semantics. This sub-optimal design invariably undermines the performance of later exits. In this paper, we propose Dynamic Perceiver (Dyn-Perceiver) to decouple the feature extraction procedure and the early classification task with a novel dual-branch architecture. A feature branch serves to extract image features, while a classification branch processes a latent code assigned for classification tasks. Bi-directional cross-attention layers are established to progressively fuse the information of both branches. Early exits are placed exclusively within the classification branch, thus eliminating the need for linear separability in low-level features. Dyn-Perceiver constitutes a versatile and adaptable framework that can be built upon various architectures. Experiments on image classification, action recognition, and object detection demonstrate that our method significantly improves the inference efficiency of different backbones, outperforming numerous competitive approaches across a broad range of computational budgets. Evaluation on both CPU and GPU platforms substantiate the superior practical efficiency of Dyn-Perceiver. Code is available at https://www.github.com/LeapLabTHU/Dynamic_Perceiver.

arXiv:2306.09537공식 코드 · Papers with Code

QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control

Reinforcement learning (RL) has shown promise in creating robust policies for robotics tasks. However, contemporary RL algorithms are data-hungry, often requiring billions of environment transitions to train successful policies. This necessitates the use of fast and highly-parallelizable simulators. In addition to speed, such simulators need to model the physics of the robots and their interaction with the environment to a level acceptable for transferring policies learned in simulation to reality. We present QuadSwarm, a fast, reliable simulator for research in single and multi-robot RL for quadrotors that addresses both issues. QuadSwarm, with fast forward-dynamics propagation decoupled from rendering, is designed to be highly parallelizable such that throughput scales linearly with additional compute. It provides multiple components tailored toward multi-robot RL, including diverse training scenarios, and provides domain randomization to facilitate the development and sim2real transfer of multi-quadrotor control policies. Initial experiments suggest that QuadSwarm achieves over 48,500 simulation samples per second (SPS) on a single quadrotor and over 62,000 SPS on eight quadrotors on a 16-core CPU. The code can be found in https://github.com/Zhehui-Huang/quad-swarm-rl.

arXiv:2306.09002공식 코드 · Papers with Code

ExoMDN: Rapid characterization of exoplanet interior structures with Mixture Density Networks

Characterizing the interior structure of exoplanets is essential for understanding their diversity, formation, and evolution. As the interior of exoplanets is inaccessible to observations, an inverse problem must be solved, where numerical structure models need to conform to observable parameters such as mass and radius. This is a highly degenerate problem whose solution often relies on computationally-expensive and time-consuming inference methods such as Markov Chain Monte Carlo. We present ExoMDN, a machine-learning model for the interior characterization of exoplanets based on Mixture Density Networks (MDN). The model is trained on a large dataset of more than 5.6 million synthetic planets below 25 Earth masses consisting of an iron core, a silicate mantle, a water and high-pressure ice layer, and a H/He atmosphere. We employ log-ratio transformations to convert the interior structure data into a form that the MDN can easily handle. Given mass, radius, and equilibrium temperature, we show that ExoMDN can deliver a full posterior distribution of mass fractions and thicknesses of each planetary layer in under a second on a standard Intel i5 CPU. Observational uncertainties can be easily accounted for through repeated predictions from within the uncertainties. We use ExoMDN to characterize the interior of 22 confirmed exoplanets with mass and radius uncertainties below 10% and 5% respectively, including the well studied GJ 1214 b, GJ 486 b, and the TRAPPIST-1 planets. We discuss the inclusion of the fluid Love number $k_2$ as an additional (potential) observable, showing how it can significantly reduce the degeneracy of interior structures. Utilizing the fast predictions of ExoMDN, we show that measuring $k_2$ with an accuracy of 10% can constrain the thickness of core and mantle of an Earth analog to $\approx13\%$ of the true values.

arXiv:2306.09106공식 코드 · Papers with Code

Audio Tagging on an Embedded Hardware Platform

Convolutional neural networks (CNNs) have exhibited state-of-the-art performance in various audio classification tasks. However, their real-time deployment remains a challenge on resource-constrained devices like embedded systems. In this paper, we analyze how the performance of large-scale pretrained audio neural networks designed for audio pattern recognition changes when deployed on a hardware such as Raspberry Pi. We empirically study the role of CPU temperature, microphone quality and audio signal volume on performance. Our experiments reveal that the continuous CPU usage results in an increased temperature that can trigger an automated slowdown mechanism in the Raspberry Pi, impacting inference latency. The quality of a microphone, specifically with affordable devices like the Google AIY Voice Kit, and audio signal volume, all affect the system performance. In the course of our investigation, we encounter substantial complications linked to library compatibility and the unique processor architecture requirements of the Raspberry Pi, making the process less straightforward compared to conventional computers (PCs). Our observations, while presenting challenges, pave the way for future researchers to develop more compact machine learning models, design heat-dissipative hardware, and select appropriate microphones when AI models are deployed for real-time applications on edge devices. All related assets and an interactive demo can be found on GitHub

arXiv:2306.09303공식 코드 · Papers with Code

Datasets and Benchmarks for Offline Safe Reinforcement Learning

This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and deployment phases. Our benchmark suite contains three packages: 1) expertly crafted safe policies, 2) D4RL-styled datasets along with environment wrappers, and 3) high-quality offline safe RL baseline implementations. We feature a methodical data collection pipeline powered by advanced safe RL algorithms, which facilitates the generation of diverse datasets across 38 popular safe RL tasks, from robot control to autonomous driving. We further introduce an array of data post-processing filters, capable of modifying each dataset's diversity, thereby simulating various data collection conditions. Additionally, we provide elegant and extensible implementations of prevalent offline safe RL algorithms to accelerate research in this area. Through extensive experiments with over 50000 CPU and 800 GPU hours of computations, we evaluate and compare the performance of these baseline algorithms on the collected datasets, offering insights into their strengths, limitations, and potential areas of improvement. Our benchmarking framework serves as a valuable resource for researchers and practitioners, facilitating the development of more robust and reliable offline safe RL solutions in safety-critical applications. The benchmark website is available at \url{www.offline-saferl.org}.

arXiv:2306.06152공식 코드 · Papers with Code

EfficientBioAI: Making Bioimaging AI Models Efficient in Energy, Latency and Representation

Artificial intelligence (AI) has been widely used in bioimage image analysis nowadays, but the efficiency of AI models, like the energy consumption and latency is not ignorable due to the growing model size and complexity, as well as the fast-growing analysis needs in modern biomedical studies. Like we can compress large images for efficient storage and sharing, we can also compress the AI models for efficient applications and deployment. In this work, we present EfficientBioAI, a plug-and-play toolbox that can compress given bioimaging AI models for them to run with significantly reduced energy cost and inference time on both CPU and GPU, without compromise on accuracy. In some cases, the prediction accuracy could even increase after compression, since the compression procedure could remove redundant information in the model representation and therefore reduce over-fitting. From four different bioimage analysis applications, we observed around 2-5 times speed-up during inference and 30-80$\%$ saving in energy. Cutting the runtime of large scale bioimage analysis from days to hours or getting a two-minutes bioimaging AI model inference done in near real-time will open new doors for method development and biomedical discoveries. We hope our toolbox will facilitate resource-constrained bioimaging AI and accelerate large-scale AI-based quantitative biological studies in an eco-friendly way, as well as stimulate further research on the efficiency of bioimaging AI.

arXiv:2305.18932공식 코드 · Papers with Code

The Information Retrieval Experiment Platform

We integrate ir_datasets, ir_measures, and PyTerrier with TIRA in the Information Retrieval Experiment Platform (TIREx) to promote more standardized, reproducible, scalable, and even blinded retrieval experiments. Standardization is achieved when a retrieval approach implements PyTerrier's interfaces and the input and output of an experiment are compatible with ir_datasets and ir_measures. However, none of this is a must for reproducibility and scalability, as TIRA can run any dockerized software locally or remotely in a cloud-native execution environment. Version control and caching ensure efficient (re)execution. TIRA allows for blind evaluation when an experiment runs on a remote server or cloud not under the control of the experimenter. The test data and ground truth are then hidden from public access, and the retrieval software has to process them in a sandbox that prevents data leaks. We currently host an instance of TIREx with 15 corpora (1.9 billion documents) on which 32 shared retrieval tasks are based. Using Docker images of 50 standard retrieval approaches, we automatically evaluated all approaches on all tasks (50 $\cdot$ 32 = 1,600~runs) in less than a week on a midsize cluster (1,620 CPU cores and 24 GPUs). This instance of TIREx is open for submissions and will be integrated with the IR Anthology, as well as released open source.

arXiv:2305.18691공식 코드 · Papers with Code

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts

Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention in ViT and the need to activate an entire large MTL model for one task. M$^3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE), where only a small portion of subnetworks ("experts") are sparsely and dynamically activated based on the current task. M$^3$ViT achieves better accuracy and over 80% computation reduction but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations, including (1) a novel reordering mechanism for self-attention, which requires only constant bandwidth regardless of the target parallelism; (2) a fast single-pass softmax approximation; (3) an accurate and low-cost GELU approximation; (4) a unified and flexible computing unit that is shared by almost all computational layers to maximally reduce resource usage; and (5) uniquely for M$^3$ViT, a novel patch reordering method to eliminate memory access overhead. Edge-MoE achieves 2.24x and 4.90x better energy efficiency comparing with GPU and CPU, respectively. A real-time video demonstration is available online, along with our open-source code written using High-Level Synthesis.

arXiv:2305.18575공식 코드 · Papers with Code

Search-Based Regular Expression Inference on a GPU

Regular expression inference (REI) is a supervised machine learning and program synthesis problem that takes a cost metric for regular expressions, and positive and negative examples of strings as input. It outputs a regular expression that is precise (i.e., accepts all positive and rejects all negative examples), and minimal w.r.t. to the cost metric. We present a novel algorithm for REI over arbitrary alphabets that is enumerative and trades off time for space. Our main algorithmic idea is to implement the search space of regular expressions succinctly as a contiguous matrix of bitvectors. Collectively, the bitvectors represent, as characteristic sequences, all sub-languages of the infix-closure of the union of positive and negative examples. Mathematically, this is a semiring of (a variant of) formal power series. Infix-closure enables bottom-up compositional construction of larger from smaller regular expressions using the operations of our semiring. This minimises data movement and data-dependent branching, hence maximises data-parallelism. In addition, the infix-closure remains unchanged during the search, hence search can be staged: first pre-compute various expensive operations, and then run the compute intensive search process. We provide two C++ implementations, one for general purpose CPUs and one for Nvidia GPUs (using CUDA). We benchmark both on Google Colab Pro: the GPU implementation is on average over 1000x faster than the CPU implementation on the hardest benchmarks.

arXiv:2305.17144공식 코드 · Papers with Code

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

The captivating realm of Minecraft has attracted substantial research interest in recent years, serving as a rich platform for developing intelligent agents capable of functioning in open-world environments. However, the current research landscape predominantly focuses on specific objectives, such as the popular "ObtainDiamond" task, and has not yet shown effective generalization to a broader spectrum of tasks. Furthermore, the current leading success rate for the "ObtainDiamond" task stands at around 20%, highlighting the limitations of Reinforcement Learning (RL) based controllers used in existing methods. To tackle these challenges, we introduce Ghost in the Minecraft (GITM), a novel framework integrates Large Language Models (LLMs) with text-based knowledge and memory, aiming to create Generally Capable Agents (GCAs) in Minecraft. These agents, equipped with the logic and common sense capabilities of LLMs, can skillfully navigate complex, sparse-reward environments with text-based interactions. We develop a set of structured actions and leverage LLMs to generate action plans for the agents to execute. The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate on the "ObtainDiamond" task, demonstrating superior robustness compared to traditional RL-based controllers. Notably, our agent is the first to procure all items in the Minecraft Overworld technology tree, demonstrating its extensive capabilities. GITM does not need any GPU for training, but a single CPU node with 32 CPU cores is enough. This research shows the potential of LLMs in developing capable agents for handling long-horizon, complex tasks and adapting to uncertainties in open-world environments. See the project website at https://github.com/OpenGVLab/GITM.

arXiv:2305.18205공식 코드 · Papers with Code

Pulse shape discrimination based on the Tempotron: a powerful classifier on GPU

This study utilized the Tempotron, a robust classifier based on a third-generation neural network model, for pulse shape discrimination. By eliminating the need for manual feature extraction, the Tempotron model can process pulse signals directly, generating discrimination results based on prior knowledge. The study performed experiments using GPU acceleration, resulting in over 500 times faster compared to the CPU-based model, and investigated the impact of noise augmentation on the Tempotron performance. Experimental results substantiated that Tempotron serves as a formidable classifier, adept at accomplishing high discrimination accuracy on both AmBe and time-of-flight PuBe datasets. Furthermore, analyzing the neural activity of Tempotron during training shed light on its learning characteristics and aided in selecting its hyperparameters. Moreover, the study addressed the constraints and potential avenues for future development in utilizing the Tempotron for pulse shape discrimination. The dataset used in this study and the GPU-based Tempotron are publicly available on GitHub at https://github.com/HaoranLiu507/TempotronGPU.

arXiv:2305.16608공식 코드 · Papers with Code

AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec

A good audio codec for live applications such as telecommunication is characterized by three key properties: (1) compression, i.e.\ the bitrate that is required to transmit the signal should be as low as possible; (2) latency, i.e.\ encoding and decoding the signal needs to be fast enough to enable communication without or with only minimal noticeable delay; and (3) reconstruction quality of the signal. In this work, we propose an open-source, streamable, and real-time neural audio codec that achieves strong performance along all three axes: it can reconstruct highly natural sounding 48~kHz speech signals while operating at only 12~kbps and running with less than 6~ms (GPU)/10~ms (CPU) latency. An efficient training paradigm is also demonstrated for developing such neural audio codecs for real-world scenarios. Both objective and subjective evaluations using the VCTK corpus are provided. To sum up, AudioDec is a well-developed plug-and-play benchmark for audio codec applications.

arXiv:2305.13905공식 코드 · Papers with Code

EfficientSpeech: An On-Device Text to Speech Model

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on speech quality with cloud inference in mind. Neural TTS models are generally not designed to perform standalone speech syntheses on resource-constrained and no Internet access edge devices. In this work, an efficient neural TTS called EfficientSpeech that synthesizes speech on an ARM CPU in real-time is proposed. EfficientSpeech uses a shallow non-autoregressive pyramid-structure transformer forming a U-Network. EfficientSpeech has 266k parameters and consumes 90 MFLOPS only or about 1% of the size and amount of computation in modern compact models such as Mixer-TTS. EfficientSpeech achieves an average mel generation real-time factor of 104.3 on an RPi4. Human evaluation shows only a slight degradation in audio quality as compared to FastSpeech2.