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_prefill_t32.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/manifest.plist +0 -0
- ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/resources.bin +2 -2
- ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_0.mpsgraph +3 -0
- ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main-h18p.mlirb +0 -0
- ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main.hash +1 -1
- ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/metadata.json +3 -3
- ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/stats.json +1 -1
.gitattributes
CHANGED
|
@@ -50,3 +50,4 @@ ios/voxcpm2_feat_decoder_fp16.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExec
|
|
| 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
|
|
|
|
|
|
| 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
|
| 53 |
+
ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main-h18p-delegates/MPSGraph/mpsExecutable.mpsgraphpackage/specialized_model_0.mpsgraph filter=lfs diff=lfs merge=lfs -text
|
ios/voxcpm2_base_int8_prefill_t32.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_prefill_t32.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 sha256:0ddcf9b1d5185aa6a07306199a3a7fe3163adc789959597caac683e3e6baf68c
|
| 3 |
+
size 1322813764
|
ios/voxcpm2_base_int8_prefill_t32.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 sha256:01bea94d6360ebf6c312cac07d32b87ae3191cc10eec8fa6af7bb53a3798b2d2
|
| 3 |
+
size 904969
|
ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main-h18p.mlirb
CHANGED
|
Binary files a/ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main-h18p.mlirb and b/ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main-h18p.mlirb differ
|
|
|
ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/main.hash
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
7������D���۶ٽ�g��;��]���=k
|
ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/metadata.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"creationDate" : "
|
| 4 |
"assetVersion" : "2.0",
|
| 5 |
-
"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"producer" : "coreai-build-3600.75.3",
|
| 3 |
+
"creationDate" : "20260720T161500Z",
|
| 4 |
"assetVersion" : "2.0",
|
| 5 |
+
"sourceHash" : "B670567B42AF4C9292A8E2B2458E9ABD112954AAB0AFE39C8A77AB0644F3FEA9"
|
| 6 |
}
|
ios/voxcpm2_base_int8_prefill_t32.h18p.aimodelc/stats.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"storageTypes":[{"name":"Int8","count":
|
|
|
|
| 1 |
+
{"storageTypes":[{"name":"Int8","count":1321216000},{"name":"Float16","count":796674},{"name":"Int32","count":4542},{"name":"UInt32","count":59},{"name":"Float32","count":3},{"name":"UInt64","count":1}],"computeTypes":["Float16","Float32","Int32","Int8","UInt32","UInt64"],"operationDistribution":[{"name":"constant","count":3472},{"count":678,"name":"reshape"},{"count":537,"name":"broadcast_in_dims"},{"name":"mul","count":423},{"name":"cast","count":370},{"name":"broadcasting_mul","count":366},{"name":"transpose","count":336},{"count":310,"name":"add"},{"name":"broadcast_to","count":282},{"name":"blockwise_shift_scale","count":253},{"name":"batch_matmul","count":252},{"count":252,"name":"broadcasting_batch_matmul"},{"name":"broadcasting_add","count":225},{"name":"concat","count":224},{"count":224,"name":"slice"},{"count":142,"name":"reduce"},{"count":113,"name":"broadcasting_divide"},{"count":113,"name":"divide"},{"name":"reduce_sum","count":85},{"name":"gather_along_axis","count":58},{"count":58,"name":"read_handle"},{"name":"broadcast_shapes","count":57},{"name":"broadcasting_pow","count":57},{"count":57,"name":"gather_nd"},{"count":57,"name":"get_shape"},{"name":"pow","count":57},{"name":"reduce_mean","count":57},{"count":57,"name":"reduce_product"},{"count":57,"name":"rsqrt"},{"name":"exp","count":56},{"count":56,"name":"slice_update"},{"name":"split","count":56},{"name":"write_handle","count":56},{"name":"broadcasting_sub","count":28},{"name":"silu","count":28},{"name":"softmax","count":28},{"count":28,"name":"sub"},{"count":1,"name":"create_token"}]}
|