Update speeds for the FP16 default

README.md

@@ -53,11 +53,11 @@ RTX 5090, Parakeet v3, LibriSpeech test-clean (5.4 h), one utterance at a time:
 
 | | Speed (x real time) | WER |
 |---|---|---|
-| scriptrs CUDA (FP16 default) | 1416x | 1.93 % |
+| scriptrs CUDA (FP16 default) | 1534x | 1.93 % |
 | 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 3443x with 8.24 % pooled WER. More results are in the [scriptrs README](https://github.com/avencera/scriptrs#cuda).
+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).
 
 ## Usage