speechbrain
SpeechBrain is an open-source PyTorch toolkit aimed at developing speech and text processing technologies. It supports many different tasks such as speech recognition, speaker recognition, speech improvement, and language Modeling. It manages training processes with YAML and Python files by offering a consistent code structure between different tasks.
speechbrain
100speechbrain · Music & Audio Technology
Common commercial products in this category: Adobe Audition, Ableton Live, Spotify
- Using the PyTorch infrastructure, you develop speech recognition and speaker recognition systems.
- You integrate pre-trained models such as Whisper, Wav2Vec2, and GPT2 into their projects and do the fine-tuning.
- You manage model training through YAML-based configuration files and Python scripts.
- • NeutralHacker News
SpeechBrain 1.0: A free and open-source AI toolkit for all things speech
“Exciting news! SpeechBrain 1.0 is out. SpeechBrain is a free and open-source AI toolkit for all things speech: speech recognition, speech synthesis, speech separation, emotion recognition and many, many other tasks. It features many state-of-the art models that can be easily…”