Real-Time Live Speech-to-Text | Streaming ASR Gradio App with Hugging Face Tutorial
Автор: 1littlecoder
Загружено: 2022-04-01
Просмотров: 29994
In this Applied NLP Tutorial, We'll learn how to build a Real-Time Automatic Speech Recognition powered by Facebooks Wav2Vec2 Deep Learning Model.
We'll learn to use Hugging Face Transformers Pipeline for Audio (Speech) to Text and Gradio for the Python Web app for live audio transcription.
Colab Notebook - https://colab.research.google.com/dri...
Deploying Gradio ML App on Hugging Face Spaces - • 9. Deploy ML Gradio App on Hugging Face Sp...
Gradio's detailed blogpost on Real-Time Speech Recognition - https://gradio.app/real_time_speech_r...
Related NLP Tutorials -
Youtube Video Transcript Summarization with Hugging Face Transformers (without ASR) - • Youtube Video Transcript Summarization wit...
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке: