Upload VoxCPM2 ONNX models (4 models, ~17GB)

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+audio_vae_decoder.onnx.data filter=lfs diff=lfs merge=lfs -text
+audio_vae_encoder.onnx.data filter=lfs diff=lfs merge=lfs -text
+voxcpm2_decode_step.onnx.data filter=lfs diff=lfs merge=lfs -text
+voxcpm2_prefill.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+tags:
+  - tts
+  - voice-cloning
+  - onnx
+  - cpu-inference
+  - cantonese
+  - voxcpm2
+language:
+  - zh
+  - en
+  - ja
+library_name: onnxruntime
+pipeline_tag: text-to-speech
+---
+
+# VoxCPM2-ONNX
+
+ONNX Runtime models for [VoxCPM2](https://github.com/OpenBMB/VoxCPM) — a 2B-parameter text-to-speech model by OpenBMB with voice cloning capability.
+
+**Run VoxCPM2 voice cloning on any CPU — no GPU needed.**
+
+## Models
+
+| File | Size | Description |
+|---|---|---|
+| `audio_vae_encoder.onnx` + `.data` | ~185 MB | Audio waveform to latent features |
+| `audio_vae_decoder.onnx` + `.data` | ~176 MB | Latent features to 48 kHz waveform |
+| `voxcpm2_prefill.onnx` + `.data` | ~7.8 GB | Text + reference audio to KV cache + DiT hidden state |
+| `voxcpm2_decode_step.onnx` + `.data` | ~8.1 GB | Single autoregressive decode step (10 CFM steps baked in) |
+
+All models use `external_data=True` — keep `.onnx` and `.onnx.data` files together.
+
+## Usage
+
+```bash
+# Install
+pip install voxcpm>=2.0.2 torch>=2.4.0 onnxruntime>=1.18.0 soundfile numpy tqdm huggingface_hub
+
+# Download models
+python -c "
+from huggingface_hub import snapshot_download
+snapshot_download('ai4all8/VoxCPM2-ONNX', local_dir='./onnx_models', ignore_patterns=['*.md', '*.txt'])
+"
+
+# Download VoxCPM2 PyTorch weights (needed for preprocessing)
+python -c "from voxcpm import VoxCPM; VoxCPM.from_pretrained('openbmb/VoxCPM2')"
+
+# Run inference (see GitHub repo for full CLI)
+git clone https://github.com/ai4all8/VoxCPM2-ONNX.git
+cd VoxCPM2-ONNX
+python infer.py --text "Hello!" --ref_wav speaker.wav --ref_text "Reference transcript."
+```
+
+Full documentation and code: [github.com/ai4all8/VoxCPM2-ONNX](https://github.com/ai4all8/VoxCPM2-ONNX)
+
+## Languages
+
+- Cantonese (粵語)
+- Mandarin (普通話)
+- English
+- Japanese (日本語)
+
+## Performance
+
+| Platform | RTF | Notes |
+|---|---|---|
+| AMD Ryzen 9 (Windows) | ~4.5x | 8 cores, ORT sequential |
+| Intel Core (Linux) | ~9.5x | Single-threaded |
+
+RTF = Real-Time Factor (lower is better; 1.0 = real-time).
+
+## License
+
+Apache License 2.0, same as the original VoxCPM2 model.
+
+## Attribution
+
+Original model: [VoxCPM2 by OpenBMB](https://github.com/OpenBMB/VoxCPM) (Apache 2.0, Copyright OpenBMB / Tsinghua University).

audio_vae_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd20e200675ab9649bf33f16bc5974101ba5cf47ab89fbfe29f3d36ff6c3c84
+size 1058148

audio_vae_decoder.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b76bd57356e96893655bd24a364989e016c5af2fc8c29195caaefb4eccf5143
+size 183042048

audio_vae_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de83b50a1f71e7bfa67f21071ffc74ae3363a7112b846040e3dfd3f2157de5b
+size 728362

audio_vae_encoder.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ccf55f431d96c34117954830ee6a783fb88f200afb03de480616172ad3a1ed
+size 192217088

voxcpm2_decode_step.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476e37924de98864c0f3afee66a9e9ffd70583805d830dc15701c56187101103
+size 20549602

voxcpm2_decode_step.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45192a7bb5b8a8222663053e0ff30f2f50f4527714619cee70c9816ce05425f5
+size 8659337216

voxcpm2_prefill.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8c7b3e783cfe59db5e6caeeabcc58bb0b6d7e7d5228fde67a59cca5266d9da
+size 6688961

voxcpm2_prefill.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c0c580da4c6ee176b9455cee8670517581b59dc097d86e8153b614b3d5e671
+size 8362196992