-
Demo of OWSM-V4 Medium model and OWSM-V4 CTC model
This app lets you upload an audio clip (up to 2 minutes) and optionally type a short text prompt. It automatically detects the spoken language, converts the speech to text, translates it if needed,...
-
How to Perform Long-Form ASR with CTC?
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech) - Speech/tutorials/asr/Streaming_ASR.ipynb at main · NVIDIA-NeMo/Speech
-
How to fine-tune pre-trained OWSM?
End-to-End Speech Processing Toolkit. Contribute to espnet/espnet development by creating an account on GitHub.