Instructions to use espnet/OpenBEATS-Large-AudioCaptioner-AudioCaps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/OpenBEATS-Large-AudioCaptioner-AudioCaps with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/OpenBEATS-Large-AudioCaptioner-AudioCaps" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
| espnet: '202503' | |
| files: | |
| asr_model_file: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/valid.acc.ave_5best.pth | |
| python: "3.9.18 | packaged by conda-forge | (main, Dec 23 2023, 17:20:25) \n[GCC 12.3.0]" | |
| timestamp: 1763334080.358429 | |
| torch: 2.1.2 | |
| yaml_files: | |
| asr_train_config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/config.yaml | |