asr-model

Fully local, private and cross platform Speech-to-Text with LLM Post-processing

Open source inference code for Rev's model

Hojo-ASR is a high-performance speech recognition model powered by the LLM decoder.

SOVA ASR (Automatic Speech Recognition)

Kroko ASR - Speech-to-text

Trained models for automatic speech recognition (ASR). A library to quickly build applications that require speech to text conversion.

End-to-End Vietnamese Speech Recognition using wav2vec 2.0

A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.

An implementation of RNN-Transducer loss in TF-2.0.

Whisper Studio is an independent desktop interface for OpenAI Whisper.

fine-tune Wav2vec2. an ASR model released by Facebook

AstraCat · 小猫做字幕，基于 LLM、Avalonia 12.1.1 与 .NET 10 的跨平台字幕软件，支持视频字幕生成、LLM断句、联网术语研究、校正翻译、字幕烧录。Powered by Whisper / QwenASR for offline, GPU-accelerated video subtitling.

Summarization, topic generation using GPT3

ComfyUI nodes for Qwen3-ASR (0.6B/1.7B) and ForcedAligner. Supports high-accuracy ASR and language identification for 52 languages/dialects, including 22 Chinese dialects and various English accents. Features word-level timestamps, long audio transcription, and VRAM-optimized inference.

Quartznet implementation on pytorch [https://arxiv.org/abs/1910.10261]

Collection and resources for Bulgarian Corpus, Datasets and Models used in ASR, TTS or NLP tasks together with the links of corresponding tools/apps.

Nemotron ASR rewrite to GGML

Automatic speech recognition (ASR) for Indonesian language built by using HTK and Julius. Web interface is built using Node.js.

Many ASRs under one roof. With Benchmarking... answering the question. What is the best ASR for my dataset?

按快捷键，说话，说完自动识别并上屏 —— 基于大模型的流式语音识别（ASR）的 Linux 语音输入工具