Open-source alternatives to Tensorflow Speech Recognition

Vosk is an offline speech-to-text engine and API that converts spoken audio into text locally on a device. It provides a cross-platform speech toolkit with language bindings for integrating voice recognition into server environments, Android, iOS, and Raspberry Pi. The project includes a speaker identification tool to distinguish between different voices and an acoustic model trainer for building custom neural network models. These training tools enable speech feature extraction and model accuracy evaluation to improve recognition for specialized domains. The system supports real-time audio

Omnilingual-ASR is a multilingual automatic speech recognition framework and toolkit designed to transcribe audio across 1,600 languages. It provides a complete pipeline for converting speech to text, including a toolkit for fine-tuning pre-trained speech models to specific languages or datasets using custom training recipes. The system supports zero-shot speech recognition, allowing the model to predict text in unseen languages without extensive training data. It further enables few-shot language guidance through in-context examples and uses language codes to constrain transcription output t

FunASR is an automatic speech recognition toolkit and multilingual speech-to-text engine designed to convert spoken audio into written text across more than fifty languages. It provides a framework for speaker diarization, an OpenAI-compatible transcription API for local server hosting, and speech models compatible with the ONNX format. The project distinguishes itself by supporting high-performance inference on edge hardware via self-contained binaries and portable model exports. It incorporates specialized capabilities for natural speech generation with adjustable timbre and emotional expre

WhisperX is an automated speech recognition toolkit designed to convert spoken audio into text while maintaining precise synchronization with the original media. It functions as an integrated pipeline that combines transcription, phoneme-based alignment, and speaker diarization to produce structured, attributed transcripts. The project distinguishes itself through its use of forced alignment, which matches existing text to audio signals at the phoneme level to generate accurate word-level timestamps. It also incorporates speaker diarization to identify and label unique voices within a recordi

AudioGPT is an LLM-driven audio framework and processing suite that uses large language models to orchestrate neural audio pipelines. It functions as a multimodal audio generator and processing system, integrating a collection of pretrained models to handle speech synthesis, sound generation, and audio manipulation. The system is distinguished by its ability to generate audio from diverse inputs, including text and images, and its capacity to produce synchronized talking head videos. It also operates as a neural speech translator, converting spoken language between different tongues while pre

This project is a speech recognition and translation engine that utilizes a sequence-to-sequence transformer architecture to convert audio into text. It is built upon a weakly supervised learning framework, which leverages large-scale, unlabelled audio-transcript data to create generalized speech representations capable of performing simultaneous transcription, language identification, and translation. The system distinguishes itself through a unified multi-task modeling approach that shares token sequences across different objectives, allowing it to handle diverse languages and vocabularies

Video analyzer is a toolkit that processes video files through computer vision and automatic speech recognition to produce structured JSON data and natural language summaries. The system extracts visual frames, samples key moments based on pixel differences, and transcribes soundtrack audio into written text to generate comprehensive descriptions across chronological timelines. The software coordinates sequential processing stages that combine frame-by-frame visual analysis with audio transcripts using local or cloud AI models. It supports adaptive and uniform frame sampling, hardware-accele

ESPnet is a comprehensive speech processing toolkit and PyTorch-based trainer designed for building end-to-end speech recognition, synthesis, and translation models. It provides a structured framework for developing automatic speech recognition systems using transducer and encoder-decoder architectures, alongside engines for text-to-speech synthesis and speech translation pipelines. The project distinguishes itself through a recipe-based workflow execution system that ensures experimental reproducibility by running standardized sequences of scripts for data preparation and model training. It

Whisper-diarization is a system for identifying and separating different speakers in audio recordings by combining OpenAI Whisper for transcription with automated speaker attribution. It functions as a pipeline that isolates vocal tracks from background noise and assigns transcribed segments to specific individuals. The project uses forced alignment to synchronize transcribed text timestamps with audio signals, improving the accuracy of speaker attribution. It employs voice activity detection to separate speech from silence and noise, ensuring precise boundaries for identification. The syste

Omi is an open-source wearable AI platform that captures audio and screen data to provide real-time conversational assistance and memory. It integrates a wearable hardware development kit with a vector memory database and large language model capabilities to create a persistent digital record of user interactions. The platform is distinguished by its BLE audio streaming pipeline, which transmits raw audio from wearable hardware for real-time transcription and speaker identification. It utilizes a plugin-based agent tool framework that allows AI assistants to autonomously invoke custom functio

Pyannote.audio is a PyTorch toolkit for speaker diarization, speaker identification, and speech activity detection. Its primary purpose is to partition audio recordings into segments and assign each segment to a specific speaker identity to determine who spoke when. The project includes a framework for classifying speaker identities and a pipeline for distinguishing human speech from background noise. It provides specialized tools for handling symmetric-overlap speech, where multiple speakers talk simultaneously, and employs learnable band-pass filters for raw waveform feature extraction. Th

This project is a deep learning framework designed for end-to-end speech-to-text transcription. It utilizes the WaveNet neural network architecture to process spoken audio input and generate written text transcripts, leveraging connectionist temporal classification to map variable-length audio sequences to character-level outputs. The system distinguishes itself through a comprehensive training pipeline that supports distributed execution across multiple graphics processing units. It includes specialized utilities for audio data augmentation and the transformation of raw audio files into opti

PyTorch is a machine learning framework centered on a GPU-ready tensor library that supports multi-dimensional array operations across both CPU and accelerator hardware. It provides a foundational infrastructure for mathematical computation and dynamic neural network construction, utilizing a tape-based automatic differentiation system that allows for flexible, non-static graph execution. The framework is designed for deep integration with Python, enabling natural usage alongside standard scientific computing ecosystems. It distinguishes itself through a comprehensive distributed training sui

Whisper.cpp is a high-performance, local-first speech recognition engine designed to run large-scale machine learning models on consumer hardware. It functions as a portable library that converts audio into text, supporting both static file transcription and real-time stream processing. By utilizing a lightweight inference engine and weight quantization, the project minimizes memory and compute overhead, allowing for efficient execution without reliance on external cloud APIs or internet connectivity. The project distinguishes itself through a hardware-agnostic compute abstraction that offloa

Pyvideotrans is an automated video localization platform designed to transcribe, translate, and dub media content for international distribution. It functions as an end-to-end workflow that combines speech recognition, text translation, and synthetic voice generation to process video files into localized versions. The system distinguishes itself by offering a choice between local model inference for privacy and integration with third-party cloud services via user-provided credentials. This architecture allows users to maintain control over their billing and data security while utilizing modul

NeMo is a comprehensive framework designed for the development, training, and deployment of large-scale conversational and generative artificial intelligence models. It provides an integrated platform for building multimodal systems, encompassing speech processing, language modeling, and reinforcement learning alignment. The framework is built to handle the entire lifecycle of AI development, from data curation and model pretraining to production-ready service deployment. The platform distinguishes itself through advanced distributed training capabilities, including tensor and pipeline parall

This is a collection of pre-trained neural models for speech recognition, synthesis, and voice activity detection. It provides a library of assets designed for speech-to-text, text-to-speech, and the identification of human speech segments within audio. The project features text-to-speech synthesis with support for multiple languages and the use of Speech Synthesis Markup Language to control prosody, pitch, and timing. For speech recognition, the system includes capabilities for transcribing audio to text with word-level timestamp extraction and an automated punctuation restorer to insert cap

Bilive is a multimodal AI video pipeline and live stream recording tool designed to capture real-time broadcasts and automate the creation of highlight clips. It functions as a multi-platform stream orchestrator capable of distributing looped pre-recorded content and managing the automated upload of processed video clips to various destinations. The system distinguishes itself through AI-driven content generation, using comment density to detect high-energy segments and multimodal models to automatically produce descriptive titles and synchronized subtitles. It further utilizes image-to-image

Distil-Whisper is a compressed automatic speech recognition model designed to convert spoken audio into written text. It uses a transformer-based sequence-to-sequence architecture to provide speech-to-text transcription. The project utilizes knowledge distillation and teacher-student model compression to create a lightweight version of the Whisper model. This approach reduces GPU memory usage and accelerates token prediction while maintaining transcription accuracy. The system supports both short-form audio transcription and long-form processing through the use of sliding windows and chunked

This project provides a self-hosted server for automatic speech recognition, functioning as a containerized inference engine for the Whisper model. It exposes core transcription and translation capabilities through a standardized web interface, allowing for the integration of speech-to-text services into external applications. The service distinguishes itself by incorporating advanced audio analysis tools, including speaker diarization to attribute text to specific individuals and voice activity detection to filter non-speech segments. It supports automated language detection and provides out

whisper-jax is a high-performance implementation of the Whisper automatic speech recognition model rewritten using the JAX framework. It is designed for accelerated inference and uses XLA compilation to optimize model execution on hardware accelerators. The project focuses on TPU optimized transcription to achieve high throughput and speed. It includes a weight translation pipeline that converts pre-trained model parameters from PyTorch into JAX-compatible arrays. The system supports transcribing audio to text, translating speech across multiple languages, and generating audio timestamps. It

Vocode-core is a framework for building real-time conversational AI voice agents. It serves as a conversational orchestrator and pipeline that integrates speech-to-text, large language models, and text-to-speech services to enable low-latency voice interactions. The project features a provider-agnostic interface that allows for swappable speech and language model providers, including support for both cloud APIs and local binaries. It distinguishes itself through a specialized telephony integration layer that enables agents to be deployed across phone lines, WebRTC, and virtual meeting platfor

whisper.cpp is a C++ implementation of the Whisper speech-to-text model, serving as a lightweight machine learning inference engine and quantized runtime. It provides high-performance automatic speech recognition and real-time audio transcription without requiring a Python environment. The project utilizes model quantization to reduce memory usage and increase inference speed on local hardware. It incorporates hardware acceleration to optimize processing speed across different processors. The system covers audio processing capabilities including voice activity detection, speaker diarization,

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Whisper is a high-performance speech-to-text inference engine that uses graphics hardware shaders to accelerate the transcription of spoken audio into written text. It implements a GPU-accelerated automatic speech recognition framework specifically designed to run Whisper models. The system focuses on high-speed processing for both recorded audio files and live microphone streams. It utilizes voice activity detection to analyze raw audio in real time, triggering the inference engine only when human speech is detected. The engine covers a broad range of capabilities including real-time audio

Cactus is an on-device AI inference engine designed for executing large language models, vision models, and speech-to-text systems on mobile and wearable hardware. It provides a programmable tensor computation graph for defining sequences of matrix operations and activation functions, alongside a local retrieval augmented generation framework that grounds model responses using local text files. The project features a multiplatform SDK with language bindings for integrating AI capabilities into mobile applications and a model conversion system that transforms external model formats for optimiz

WeNet is an end-to-end automatic speech recognition (ASR) toolkit designed for both Chinese and English, built around transformer-based models. It supports streaming and non-streaming inference out of the box, and is structured to be production-ready, with model export and deployment paths for servers and mobile devices. The toolkit distinguishes itself through a chunk-based streaming transformer architecture that processes audio in fixed-size segments for low latency while preserving context across chunks. It jointly trains models with both CTC and attention loss to combine alignment accurac