Instructions to use espnet/DCASE23.AudioCaptioning.PreTrained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/DCASE23.AudioCaptioning.PreTrained with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/DCASE23.AudioCaptioning.PreTrained" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
metadata
tags:
- espnet
- audio
- automatic-speech-recognition
- audio_captioning
language: en
datasets:
- clotho_v2
- slseanwu/clotho-chatgpt-mixup-50K
- audiocaps
license: cc-by-4.0