Instructions to use espnet/UniverSLU-17-Task-Specifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/UniverSLU-17-Task-Specifier with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/UniverSLU-17-Task-Specifier" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Download meta.yaml from espnet/UniverSLU-17-Task-Specifier: direct link, hf CLI and curl.
- Browser
- Download file 256 Bytes
-
https://huggingface.co/espnet/UniverSLU-17-Task-Specifier/resolve/main/meta.yaml
- Command line
-
hf download hf://espnet/UniverSLU-17-Task-Specifier/meta.yaml
-
curl -L -o meta.yaml https://huggingface.co/espnet/UniverSLU-17-Task-Specifier/resolve/main/meta.yaml
256 Bytes
| files: | |
| asr_model_file: exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/valid.acc.ave_10best.pth | |
| yaml_files: | |
| asr_train_config: exp/asr_train_asr_whisper_full_correct_specaug2_copy_raw_en_whisper_multilingual/config.yaml | |