Ecosyste.ms: Repos
An open API service providing repository metadata for many open source software ecosystems.
GitHub / skit-ai / Multimodal-Slu
This repo builds an top of self-supervised speech embeddings using S3PL tool-kit and Text based transformers from Huggingface to explore multi-modal SLU
JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/skit-ai%2FMultimodal-Slu
Stars: 6
Forks: 1
Open Issues: 2
License: mit
Language: Python
Repo Size: 135 MB
Dependencies:
28
Created: about 3 years ago
Updated: about 2 months ago
Last pushed: about 3 years ago
Last synced: about 2 months ago
Files
Loading...
Readme
Loading...
Dependencies
requirements.txt
pypi
- Pillow >=6.2.2
- PyYAML ==5.1.2
- gdown >=3.12.2
- joblib ==0.12.4
- librosa ==0.7.2
- matplotlib >=3.3.4
- numba ==0.48
- numpy >=1.19.5
- pandas >=1.1.5
- scipy >=1.5.4
- tensorboardX ==1.9
- torch ==1.7.0
- torchaudio ==0.7.0
- torchvision ==0.8.0
- tqdm ==4.56.0
- gluonnlp ==0.8.3
- mxnet-cu102mkl *
- SoundFile *
- cupy-cuda102 *
- pynvrtc ==8.0
- pysptk ==0.1.16
- python_speech_features ==0.6
- scikit_learn *
- webrtcvad ==2.0.10
- fairseq ==0.10.2
- fairseq ==0.10.2
- fairseq ==0.10.2
- fairseq ==0.10.2