Update model card: add pretrain encoder/decoder to contents table

Add pretrain decoder checkpoint

Add pretrain encoder checkpoint

Add pretrain decoder config

Add pretrain encoder config

Clear pretrained paths (not needed for inference)

Add architecture figure to model card

Add architecture figure

Add model card

Add MFA alignment results (tar.gz)

Add spatial environment captions

Delete pretrain_encoder/model_ckpt_best.pt with huggingface_hub

Delete pretrain_encoder/config.yaml with huggingface_hub

Delete pretrain_decoder/model_ckpt_best.pt with huggingface_hub

Delete pretrain_decoder/config.yaml with huggingface_hub

Fix diff_decoder_type: remove F5 naming

Upload pretrain_decoder/config.yaml with huggingface_hub

Upload pretrain_encoder/config.yaml with huggingface_hub

Upload m2se_vtts/config.yaml with huggingface_hub

Upload pretrain_decoder/model_ckpt_best.pt with huggingface_hub

Upload pretrain_decoder/config.yaml with huggingface_hub

Upload pretrain_encoder/model_ckpt_best.pt with huggingface_hub

Upload pretrain_encoder/config.yaml with huggingface_hub

Delete pretrain_decoder_emilia/model_ckpt_best.pt with huggingface_hub

Delete pretrain_decoder_emilia/config.yaml with huggingface_hub

Delete pretrain_encoder_emilia/model_ckpt_best.pt with huggingface_hub

Delete pretrain_encoder_emilia/config.yaml with huggingface_hub

Upload m2se_vtts/model_ckpt_best.pt with huggingface_hub

Upload m2se_vtts/config.yaml with huggingface_hub

Upload pretrain_decoder_emilia/model_ckpt_best.pt with huggingface_hub

Upload pretrain_decoder_emilia/config.yaml with huggingface_hub

Upload pretrain_encoder_emilia/model_ckpt_best.pt with huggingface_hub

Upload pretrain_encoder_emilia/config.yaml with huggingface_hub

Upload bigvgan/g_00076000 with huggingface_hub

Upload bigvgan/config.json with huggingface_hub

initial commit