| { |
| "version": 1, |
| "model_type": "zipvoice_distill", |
| "encoder": { |
| "name": "encoder_core", |
| "file": "encoder.axmodel", |
| "inputs": [ |
| "cat_tokens" |
| ], |
| "outputs": [ |
| "encoded" |
| ] |
| }, |
| "decoder_parts": [ |
| { |
| "name": "fm_decoder_part0", |
| "file": "decoder_part0.axmodel", |
| "inputs": [ |
| "t", |
| "x", |
| "text_condition", |
| "speech_condition", |
| "guidance_scale", |
| "padding_mask" |
| ], |
| "outputs": [ |
| "decoder_hidden_p0", |
| "time_hidden" |
| ] |
| }, |
| { |
| "name": "fm_decoder_part1", |
| "file": "decoder_part1.axmodel", |
| "inputs": [ |
| "decoder_hidden_p0", |
| "time_hidden", |
| "padding_mask" |
| ], |
| "outputs": [ |
| "decoder_hidden_p1" |
| ] |
| }, |
| { |
| "name": "fm_decoder_part2", |
| "file": "decoder_part2.axmodel", |
| "inputs": [ |
| "decoder_hidden_p1", |
| "time_hidden", |
| "padding_mask" |
| ], |
| "outputs": [ |
| "decoder_hidden_p2" |
| ] |
| }, |
| { |
| "name": "fm_decoder_part3_0", |
| "file": "decoder_part3_0.axmodel", |
| "inputs": [ |
| "decoder_hidden_p2", |
| "time_hidden", |
| "padding_mask" |
| ], |
| "outputs": [ |
| "/fm_decoder/4/0/bypass/Add_output_0" |
| ] |
| }, |
| { |
| "name": "fm_decoder_part3_1", |
| "file": "decoder_part3_1.axmodel", |
| "inputs": [ |
| "/fm_decoder/4/0/bypass/Add_output_0", |
| "time_hidden", |
| "padding_mask" |
| ], |
| "outputs": [ |
| "/fm_decoder/4/1/bypass/Add_output_0" |
| ] |
| }, |
| { |
| "name": "fm_decoder_part3_2", |
| "file": "decoder_part3_2.axmodel", |
| "inputs": [ |
| "/fm_decoder/4/1/bypass/Add_output_0", |
| "time_hidden", |
| "padding_mask" |
| ], |
| "outputs": [ |
| "/fm_decoder/4/2/bypass/Add_output_0" |
| ] |
| }, |
| { |
| "name": "fm_decoder_part3_3", |
| "file": "decoder_part3_3.axmodel", |
| "inputs": [ |
| "/fm_decoder/4/2/bypass/Add_output_0", |
| "time_hidden", |
| "padding_mask" |
| ], |
| "outputs": [ |
| "v" |
| ] |
| } |
| ] |
| } |