Instructions to use mlboydaisuke/VoxCPM2-CoreAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use mlboydaisuke/VoxCPM2-CoreAI with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("mlboydaisuke/VoxCPM2-CoreAI") wav = model.generate( text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.", prompt_wav_path=None, # optional: path to a prompt speech for voice cloning prompt_text=None, # optional: reference text cfg_value=2.0, # LM guidance on LocDiT, higher for better adherence to the prompt, but maybe worse inference_timesteps=10, # LocDiT inference timesteps, higher for better result, lower for fast speed normalize=True, # enable external TN tool denoise=True, # enable external Denoise tool retry_badcase=True, # enable retrying mode for some bad cases (unstoppable) retry_badcase_max_times=3, # maximum retrying times retry_badcase_ratio_threshold=6.0, # maximum length restriction for bad case detection (simple but effective), it could be adjusted for slow pace speech ) sf.write("output.wav", wav, 16000) print("saved: output.wav") - Notebooks
- Google Colab
- Kaggle
host glue
Browse files- voxcpm2_host_glue/embed_tokens.bin +3 -0
- voxcpm2_host_glue/fsq_in_b.bin +3 -0
- voxcpm2_host_glue/fsq_in_w.bin +3 -0
- voxcpm2_host_glue/fsq_out_b.bin +3 -0
- voxcpm2_host_glue/fsq_out_w.bin +3 -0
- voxcpm2_host_glue/fusion_b.bin +3 -0
- voxcpm2_host_glue/fusion_w.bin +3 -0
- voxcpm2_host_glue/lm_to_dit_b.bin +3 -0
- voxcpm2_host_glue/lm_to_dit_w.bin +3 -0
- voxcpm2_host_glue/manifest.json +108 -0
- voxcpm2_host_glue/res_to_dit_b.bin +3 -0
- voxcpm2_host_glue/res_to_dit_w.bin +3 -0
- voxcpm2_host_glue/stop_head_w.bin +3 -0
- voxcpm2_host_glue/stop_proj_b.bin +3 -0
- voxcpm2_host_glue/stop_proj_w.bin +3 -0
voxcpm2_host_glue/embed_tokens.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4321641ac7a837ba3be585c73cca686159724577abaa16f16926b636bb4549c
|
| 3 |
+
size 300843008
|
voxcpm2_host_glue/fsq_in_b.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2941a0241a0655b665f8a4e7f9ecf4fef48a42dde4d5faed90b1691df569f33c
|
| 3 |
+
size 2048
|
voxcpm2_host_glue/fsq_in_w.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdca3c2a1bee2b659610156a6d381e0a8366a24a51b6972d1892f69ab7d51a11
|
| 3 |
+
size 4194304
|
voxcpm2_host_glue/fsq_out_b.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9038ceae836cbd4fcd435b47a9d1b21c669852e9ddb15483d9addeeb1c2e1c0
|
| 3 |
+
size 8192
|
voxcpm2_host_glue/fsq_out_w.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01782ab563b11a0a1425aa50ea9bd9abd23a32ffbfd28dac9bd94903e047ac09
|
| 3 |
+
size 4194304
|
voxcpm2_host_glue/fusion_b.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d5354fbd85eefa5c84b60a507000803e285ff744c9e2c9ee1003426e498c257
|
| 3 |
+
size 8192
|
voxcpm2_host_glue/fusion_w.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e692759ba614ad0e21b4193a39388227aca48fbeccd6b7142fd377cbc0923166
|
| 3 |
+
size 33554432
|
voxcpm2_host_glue/lm_to_dit_b.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864a519a0bf4b831534355a0974af37577186a2ed3ec5d1f22bf3c7ccd8af861
|
| 3 |
+
size 4096
|
voxcpm2_host_glue/lm_to_dit_w.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fe82c220796098cf019b0e13d820032b89a485b010e29e85c1133cacb71d2f3
|
| 3 |
+
size 8388608
|
voxcpm2_host_glue/manifest.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embed_tokens": {
|
| 3 |
+
"dtype": "float16",
|
| 4 |
+
"shape": [
|
| 5 |
+
73448,
|
| 6 |
+
2048
|
| 7 |
+
],
|
| 8 |
+
"bytes": 300843008
|
| 9 |
+
},
|
| 10 |
+
"lm_to_dit_w": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"shape": [
|
| 13 |
+
1024,
|
| 14 |
+
2048
|
| 15 |
+
],
|
| 16 |
+
"bytes": 8388608
|
| 17 |
+
},
|
| 18 |
+
"lm_to_dit_b": {
|
| 19 |
+
"dtype": "float32",
|
| 20 |
+
"shape": [
|
| 21 |
+
1024
|
| 22 |
+
],
|
| 23 |
+
"bytes": 4096
|
| 24 |
+
},
|
| 25 |
+
"res_to_dit_w": {
|
| 26 |
+
"dtype": "float32",
|
| 27 |
+
"shape": [
|
| 28 |
+
1024,
|
| 29 |
+
2048
|
| 30 |
+
],
|
| 31 |
+
"bytes": 8388608
|
| 32 |
+
},
|
| 33 |
+
"res_to_dit_b": {
|
| 34 |
+
"dtype": "float32",
|
| 35 |
+
"shape": [
|
| 36 |
+
1024
|
| 37 |
+
],
|
| 38 |
+
"bytes": 4096
|
| 39 |
+
},
|
| 40 |
+
"fusion_w": {
|
| 41 |
+
"dtype": "float32",
|
| 42 |
+
"shape": [
|
| 43 |
+
2048,
|
| 44 |
+
4096
|
| 45 |
+
],
|
| 46 |
+
"bytes": 33554432
|
| 47 |
+
},
|
| 48 |
+
"fusion_b": {
|
| 49 |
+
"dtype": "float32",
|
| 50 |
+
"shape": [
|
| 51 |
+
2048
|
| 52 |
+
],
|
| 53 |
+
"bytes": 8192
|
| 54 |
+
},
|
| 55 |
+
"fsq_in_w": {
|
| 56 |
+
"dtype": "float32",
|
| 57 |
+
"shape": [
|
| 58 |
+
512,
|
| 59 |
+
2048
|
| 60 |
+
],
|
| 61 |
+
"bytes": 4194304
|
| 62 |
+
},
|
| 63 |
+
"fsq_in_b": {
|
| 64 |
+
"dtype": "float32",
|
| 65 |
+
"shape": [
|
| 66 |
+
512
|
| 67 |
+
],
|
| 68 |
+
"bytes": 2048
|
| 69 |
+
},
|
| 70 |
+
"fsq_out_w": {
|
| 71 |
+
"dtype": "float32",
|
| 72 |
+
"shape": [
|
| 73 |
+
2048,
|
| 74 |
+
512
|
| 75 |
+
],
|
| 76 |
+
"bytes": 4194304
|
| 77 |
+
},
|
| 78 |
+
"fsq_out_b": {
|
| 79 |
+
"dtype": "float32",
|
| 80 |
+
"shape": [
|
| 81 |
+
2048
|
| 82 |
+
],
|
| 83 |
+
"bytes": 8192
|
| 84 |
+
},
|
| 85 |
+
"stop_proj_w": {
|
| 86 |
+
"dtype": "float32",
|
| 87 |
+
"shape": [
|
| 88 |
+
2048,
|
| 89 |
+
2048
|
| 90 |
+
],
|
| 91 |
+
"bytes": 16777216
|
| 92 |
+
},
|
| 93 |
+
"stop_proj_b": {
|
| 94 |
+
"dtype": "float32",
|
| 95 |
+
"shape": [
|
| 96 |
+
2048
|
| 97 |
+
],
|
| 98 |
+
"bytes": 8192
|
| 99 |
+
},
|
| 100 |
+
"stop_head_w": {
|
| 101 |
+
"dtype": "float32",
|
| 102 |
+
"shape": [
|
| 103 |
+
2,
|
| 104 |
+
2048
|
| 105 |
+
],
|
| 106 |
+
"bytes": 16384
|
| 107 |
+
}
|
| 108 |
+
}
|
voxcpm2_host_glue/res_to_dit_b.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97dffc1bc2a020f8dce0cec2ad6c22b70e4edf36f9423402806eb24ff066d67f
|
| 3 |
+
size 4096
|
voxcpm2_host_glue/res_to_dit_w.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47e11d162ffcfeb1bc628e40c257a1661b07979d44f9487ae835b77807a0cdd6
|
| 3 |
+
size 8388608
|
voxcpm2_host_glue/stop_head_w.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2efc98b6d2a488447eb086f105ea7b74db62bb8a5f8a1dba2ac1ad38d5653201
|
| 3 |
+
size 16384
|
voxcpm2_host_glue/stop_proj_b.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a175bdc6b145aafeff09276bc82663794388742815f471466894d825293e541d
|
| 3 |
+
size 8192
|
voxcpm2_host_glue/stop_proj_w.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e11cd25ddea908c7305fc72bd9ddc380805562d32e0f6953caba55604c94f541
|
| 3 |
+
size 16777216
|