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
File size: 236 Bytes
f8585bb | 1 2 3 4 5 6 7 8 9 | espnet: '202409'
files:
asr_model_file: exp/asr_pt/valid.acc.ave_5best.pth
python: "3.9.20 (main, Oct 3 2024, 07:27:41) \n[GCC 11.2.0]"
timestamp: 1732975453.840757
torch: 2.4.0
yaml_files:
asr_train_config: exp/asr_pt/config.yaml
|