Point the card at scriptrs 0.3 and add more speeds

README.md

@@ -57,16 +57,25 @@ RTX 5090, Parakeet v3, LibriSpeech test-clean (5.4 h), one utterance at a time:
 | NVIDIA NeMo (PyTorch) | 477x | 1.93 % |
 | parakeet-rs 0.4.3 (ONNX Runtime) | 253x | 1.93 % |
 
-On the 44 Earnings-21 calls (39 h), long-form runs at 3630x with 8.24 % pooled WER. Batched through the queue, LibriSpeech runs at 4770x. More results are in the [scriptrs README](https://github.com/avencera/scriptrs#cuda).
+More scriptrs CUDA results on the same GPU and model:
+
+| Workload | Speed (x real time) | WER |
+|---|---|---|
+| LibriSpeech test-clean, batches of 16 through the queue | 4767x | 1.93 % |
+| Earnings-21, 44 calls (39 h), long-form | 3633x | 8.24 % |
+| FLEURS de, es, fr, it, nl, pt (15.8 h) | 1839x | 4.57 % |
+| MLS es, fr, it, pt (15.8 h) | 1921x | 6.25 % |
+
+More results are in the [scriptrs README](https://github.com/avencera/scriptrs#cuda).
 
 ## Usage
 
 ```toml
 # macOS, Core ML
-scriptrs = "0.2"
+scriptrs = "0.3"
 
-# Linux, NVIDIA GPU (not yet in a crates.io release)
-scriptrs = { git = "https://github.com/avencera/scriptrs", features = ["cuda"] }
+# Linux, NVIDIA GPU
+scriptrs = { version = "0.3", features = ["cuda"] }
 ```
 
 ```rust