cantonese-hubert-base-l9-k200
This is a fine-tuned Hubert model based on TencentGameMate/chinese-hubert-base for generate speech discete units, The K-means model is trained on 9k+ hours Cantonese speech data, with 200 clusters and representations from 9th layer of the model.
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for hon9kon9ize/cantonese-hubert-base-l9-k200
Base model
TencentGameMate/chinese-hubert-base
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub models, cfg, task = load_model_ensemble_and_task_from_hf_hub( "hon9kon9ize/cantonese-hubert-base-l9-k200" )