Update model card with demo audio + eval results

README.md

@@ -14,27 +14,17 @@ base_model: openbmb/VoxCPM2
 
 LoRA adapter fine-tuned on VoxCPM2 for bedtime story narration in English.
 
-## Training details
-- **Base model**: `openbmb/VoxCPM2`
+## Training
+- **Base**: `openbmb/VoxCPM2`
 - **Dataset**: LJSpeech (6,550 clips, ~12h — half-data experiment)
 - **Method**: LoRA (r=32, alpha=64, targeting DiT attention layers)
-- **Best experiment**: exp6 (r=32, lr=5e-5, half data)
-- **Validation loss**: 0.872 (best across 6 experiments)
+- **Best**: exp6 (r=32, lr=5e-5, half data) — val loss 0.872
 - **GPU**: A100-80GB via Modal
 
-## How to use
+## Evaluation (6 experiments)
 
-```python
-from voxcpm import VoxCPM
-
-model = VoxCPM.from_pretrained("openbmb/VoxCPM2", device="cuda", load_denoiser=True, optimize=True)
-# Apply LoRA weights manually or load via adapter
-```
-
-## Evaluation results
-
-| Experiment | Config | Train Loss | Val Loss |
-|-----------|--------|-----------|----------|
+| Exp | Config | Train Loss | Val Loss |
+|-----|--------|-----------|----------|
 | exp1 | r32, lr=1e-4 | 0.823 | 0.918 |
 | exp2 | r16, lr=5e-5 | 0.765 | 0.899 |
 | exp3 | r64, lr=1e-4 | 0.838 | 0.908 |
@@ -42,5 +32,31 @@ model = VoxCPM.from_pretrained("openbmb/VoxCPM2", device="cuda", load_denoiser=T
 | exp5 | r32, lr=2e-4 | 0.832 | 0.896 |
 | **exp6** | **r32, lr=5e-5, half data** | **0.935** | **0.872** |
 
+## Demo Audio
+
+### English bedtime stories (VoxCPM2)
+
+| Mood | Audio |
+|------|-------|
+| Magical | [english_magical_mid.wav](samples/english_magical_mid.wav) |
+| Funny | [english_funny_high.wav](samples/english_funny_high.wav) |
+| Calming | [english_calming_low.wav](samples/english_calming_low.wav) |
+| Dreamy | [english_dreamy_low.wav](samples/english_dreamy_low.wav) |
+
+### LoRA vs Stock comparison
+
+| Type | Audio |
+|------|-------|
+| Stock VoxCPM2 | [comparison_stock_0.wav](samples/comparison_stock_0.wav) |
+| LoRA exp6 | [comparison_lora_exp6_0.wav](samples/comparison_lora_exp6_0.wav) |
+
+### Reference voice
+- [reference_voice.wav](samples/reference_voice.wav) — voice used for cloning
+
+## Files
+- `lora_weights.safetensors` — LoRA adapter weights (12.8 MB)
+- `lora_config.json` — LoRA configuration
+- `training_state.json` — Training state
+
 ## Part of DreamVoice
-This model is part of [DreamVoice](https://huggingface.co/spaces/build-small-hackathon/dreamvoice) — bedtime stories in a parent's cloned voice.
+[DreamVoice](https://huggingface.co/spaces/build-small-hackathon/dreamvoice) — bedtime stories in a parent's cloned voice.