Upload N1-655 CVflow v3 HiFiGAN NVP model

README.md

@@ -0,0 +1,20 @@
+---
+library_name: pytorch
+license: mit
+---
+
+# HiFi-GAN v1 Neural Vocoder (Ambarella N1-655 CVflow v3 NVP)
+
+Model Configuration:
+- Upstream source: [https://huggingface.co/csukuangfj/sherpa-onnx-hifigan](https://huggingface.co/csukuangfj/sherpa-onnx-hifigan)
+- Support Cooper version:
+  - CNNGen: `[3.9.0 / n1-655x]` (`cavalry_gen 3.0.4`)
+
+## NVP Port & Runtime Specification
+- **Target SoC**: Ambarella N1-655 (`vdg_arch = 0xB`, CVflow v3 `cavalry_gen` 3.0.4)
+- **Input port**: `mel` `[1, 80, 50]` IEEE FP16 (run with 50-frame overlap tiling: `core=20` frames, `ctx=15` context frames on each side)
+- **Output port**: `audio` `[1, 12800]` IEEE FP16 per tile (crop middle `20 * 256 = 5120` samples per tile @ 22.05 kHz)
+
+| Model | Device | Compression | Model Link |
+| :---: | :---: | :---: | :--- |
+| HiFiGAN | N1-655 | Amba_optimized | [Model_Link](https://huggingface.co/cchiou-amba/HiFiGAN/blob/main/n1-655_hifigan_vocoder_amba_optimized.bin) |

config.json

@@ -0,0 +1,3 @@
+{
+  "model_type": "llama"
+}

n1-655_hifigan_vocoder_amba_optimized.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f1b7e0c475bfee0b65dacadcb353d16752605ad1d5f0542014abf71255ee69f
+size 28999048