voxpm2-ncnn / model.json
lyrin's picture
Update fp16 KV-cache ncnn assets
b143f28 verified
Raw
History Blame Contribute Delete
5.61 kB
{
"model_type": "voxcpm2_tts",
"format_version": 2,
"params": {
"text_embed": {
"param": "text_embed.ncnn.param",
"bin": "text_embed.ncnn.bin"
},
"base_decoder_kv": {
"param": "base_decoder_kv.ncnn.param",
"bin": "base_decoder_kv.ncnn.bin"
},
"residual_decoder_kv": {
"param": "residual_decoder_kv.ncnn.param",
"bin": "residual_decoder_kv.ncnn.bin"
},
"fsq": {
"param": "fsq.ncnn.param",
"bin": "fsq.ncnn.bin"
},
"fusion_proj": {
"param": "fusion_proj.ncnn.param",
"bin": "fusion_proj.ncnn.bin"
},
"dit_proj": {
"param": "dit_proj.ncnn.param",
"bin": "dit_proj.ncnn.bin"
},
"stop_head": {
"param": "stop_head.ncnn.param",
"bin": "stop_head.ncnn.bin"
},
"feat_encoder": {
"param": "feat_encoder.ncnn.param",
"bin": "feat_encoder.ncnn.bin"
},
"dit_estimator": {
"param": "dit_estimator.ncnn.param",
"bin": "dit_estimator.ncnn.bin"
},
"audio_vae_encoder": {
"param": "audio_vae_encoder.ncnn.param",
"bin": "audio_vae_encoder.ncnn.bin"
},
"audio_vae_decoder": {
"param": "audio_vae_decoder.ncnn.param",
"bin": "audio_vae_decoder.ncnn.bin"
}
},
"missing_components": [],
"tokenizer": {
"type": "voxcpm2_tokenizer_json",
"tokenizer_json": "tokenizer.json",
"split_multichar_cjk": true
},
"setting": {
"patch_size": 4,
"feat_dim": 64,
"latent_dim": 64,
"chunk_size": 640,
"decode_chunk_size": 1920,
"encode_sample_rate": 16000,
"out_sample_rate": 48000,
"base_attn_cnt": 28,
"residual_attn_cnt": 8,
"tokens": {
"audio_start": 101,
"audio_end": 102,
"ref_audio_start": 103,
"ref_audio_end": 104
},
"rope": {
"type": "LongRoPE",
"rope_head_dim": 128,
"rope_theta": 10000.0,
"original_max_position_embeddings": 32768,
"short_factor": [
0.9977997200264581,
1.014658295992452,
1.0349680404997148,
1.059429246056193,
1.0888815016813513,
1.1243301355211495,
1.166977103606075,
1.2182568066927284,
1.2798772354275727,
1.3538666751582975,
1.4426259039919596,
1.5489853358570191,
1.6762658237220625,
1.8283407612492941,
2.0096956085876183,
2.225478927469756,
2.481536379650452,
2.784415934557119,
3.1413289096347365,
3.560047844772632,
4.048719380066383,
4.615569542115128,
5.2684819496549835,
6.014438591970396,
6.858830049237097,
7.804668263503327,
8.851768731513417,
9.99600492938444,
11.228766118181639,
12.536757560834843,
13.902257701387796,
15.303885189125953,
16.717837610115794,
18.119465097853947,
19.484965238406907,
20.792956681060105,
22.02571786985731,
23.16995406772833,
24.217054535738416,
25.16289275000465,
26.007284207271347,
26.753240849586767,
27.40615325712662,
27.973003419175363,
28.461674954469114,
28.880393889607006,
29.237306864684626,
29.540186419591297,
29.79624387177199,
30.01202719065413,
30.193382037992453,
30.34545697551969,
30.47273746338473,
30.579096895249787,
30.66785612408345,
30.741845563814174,
30.80346599254902,
30.85474569563567,
30.897392663720595,
30.932841297560394,
30.962293553185553,
30.986754758742034,
31.007064503249293,
31.02392307921529
],
"long_factor": [
0.9977997200264581,
1.014658295992452,
1.0349680404997148,
1.059429246056193,
1.0888815016813513,
1.1243301355211495,
1.166977103606075,
1.2182568066927284,
1.2798772354275727,
1.3538666751582975,
1.4426259039919596,
1.5489853358570191,
1.6762658237220625,
1.8283407612492941,
2.0096956085876183,
2.225478927469756,
2.481536379650452,
2.784415934557119,
3.1413289096347365,
3.560047844772632,
4.048719380066383,
4.615569542115128,
5.2684819496549835,
6.014438591970396,
6.858830049237097,
7.804668263503327,
8.851768731513417,
9.99600492938444,
11.228766118181639,
12.536757560834843,
13.902257701387796,
15.303885189125953,
16.717837610115794,
18.119465097853947,
19.484965238406907,
20.792956681060105,
22.02571786985731,
23.16995406772833,
24.217054535738416,
25.16289275000465,
26.007284207271347,
26.753240849586767,
27.40615325712662,
27.973003419175363,
28.461674954469114,
28.880393889607006,
29.237306864684626,
29.540186419591297,
29.79624387177199,
30.01202719065413,
30.193382037992453,
30.34545697551969,
30.47273746338473,
30.579096895249787,
30.66785612408345,
30.741845563814174,
30.80346599254902,
30.85474569563567,
30.897392663720595,
30.932841297560394,
30.962293553185553,
30.986754758742034,
31.007064503249293,
31.02392307921529
]
},
"decoder_context_length": 4,
"kv_head_cnt": 2
}
}