How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
The main features of stepfun-ai/step-audio2 are: Speech Processing, Speech Recognition.
Projects with overlapping indexed features include: openai/whisper — This project is a speech recognition and translation engine that utilizes a sequence-to-sequence transformer… xzf-thu/mega-asr. facebookresearch/omnilingual-asr — Omnilingual-ASR is a multilingual automatic speech recognition framework and toolkit designed to transcribe audio… kyutai-labs/delayed-streams-modeling — Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework. qwenlm/qwen3-asr. bytedance/megatts3 — MegaTTS3 is a bilingual speech synthesis system that generates natural-sounding speech in Chinese and English,…
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
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
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
