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
Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure)
Browse files- .gitattributes +1 -0
- ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/manifest.plist +0 -0
- ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/resources.bin +2 -2
- ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_0.mpsgraph +3 -0
- ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p.mlirb +0 -0
- ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main.hash +1 -1
- ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/metadata.json +4 -4
- ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/stats.json +1 -1
.gitattributes
CHANGED
|
@@ -49,3 +49,4 @@ ios/voxcpm2_res_int8_prefill_t32.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsE
|
|
| 49 |
ios/voxcpm2_feat_decoder_fp16.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/original_model_0.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
| 50 |
ios/voxcpm2_feat_decoder_fp16.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_1.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
| 51 |
ios/voxcpm2_feat_encoder_fp16.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_1.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 49 |
ios/voxcpm2_feat_decoder_fp16.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/original_model_0.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
| 50 |
ios/voxcpm2_feat_decoder_fp16.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_1.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
| 51 |
ios/voxcpm2_feat_encoder_fp16.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_1.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_0.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/manifest.plist
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/resources.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5609781967e79ad462f43693ff6f138bf277e047204d396d8b697d34b9ef3a9d
|
| 3 |
+
size 1322766656
|
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_0.mpsgraph
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bc0438b21f1b907a65302aa54ec056b27c5681aa4dc333828cdd37f9de2ee53
|
| 3 |
+
size 884174
|
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p.mlirb
CHANGED
|
Binary files a/ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p.mlirb and b/ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main-h18p.mlirb differ
|
|
|
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/main.hash
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
Zd��Q*�?�0B��W�/���T���zlі�&
|
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/metadata.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"sourceHash" : "
|
| 5 |
-
"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"producer" : "coreai-build-3600.75.3",
|
| 3 |
+
"assetVersion" : "2.0",
|
| 4 |
+
"sourceHash" : "E14D0923148D1F82F37E0ED56425E4E0BF3EB2388CA086F2D7C69BCFDC8F10B0",
|
| 5 |
+
"creationDate" : "20260720T161457Z"
|
| 6 |
}
|
ios/voxcpm2_base_int8_decode_cl512.h18p.aimodelc/stats.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"
|
|
|
|
| 1 |
+
{"storageTypes":[{"name":"Int8","count":1321216000},{"count":780291,"name":"Float16"},{"name":"Int32","count":838},{"name":"UInt32","count":55},{"name":"Float32","count":3},{"count":1,"name":"UInt64"}],"computeTypes":["Bool","Float16","Float32","Int32","Int8","UInt32","UInt64"],"operationDistribution":[{"count":3252,"name":"constant"},{"count":653,"name":"reshape"},{"name":"broadcast_in_dims","count":426},{"count":424,"name":"mul"},{"count":371,"name":"cast"},{"count":367,"name":"broadcasting_mul"},{"name":"add","count":311},{"name":"broadcast_to","count":282},{"count":280,"name":"concat"},{"count":253,"name":"blockwise_shift_scale"},{"count":252,"name":"batch_matmul"},{"count":252,"name":"broadcasting_batch_matmul"},{"count":226,"name":"broadcasting_add"},{"count":224,"name":"slice"},{"name":"transpose","count":224},{"count":142,"name":"reduce"},{"count":113,"name":"broadcasting_divide"},{"name":"divide","count":113},{"name":"reduce_sum","count":85},{"name":"gather_along_axis","count":58},{"count":58,"name":"read_handle"},{"count":57,"name":"broadcast_shapes"},{"count":57,"name":"broadcasting_pow"},{"count":57,"name":"gather_nd"},{"name":"get_shape","count":57},{"count":57,"name":"pow"},{"count":57,"name":"reduce_mean"},{"count":57,"name":"reduce_product"},{"name":"rsqrt","count":57},{"count":56,"name":"exp"},{"name":"slice_update","count":56},{"name":"split","count":56},{"count":56,"name":"write_handle"},{"name":"broadcasting_sub","count":28},{"name":"silu","count":28},{"name":"softmax","count":28},{"count":28,"name":"sub"},{"count":2,"name":"not"},{"name":"broadcasting_greater","count":1},{"count":1,"name":"create_token"},{"name":"greater","count":1}]}
|