Perf: load audio tokenizer directly in bf16 (skip fp32 intermediate)

src/mimo_audio/mimo_audio.py

@@ -115,9 +115,12 @@ class MimoAudio:
         }
 
         start_loading_mimo_audio_tokenizer_time = time.monotonic()
-        self.mimo_audio_tokenizer = MiMoAudioTokenizer.from_pretrained(self.mimo_audio_tokenizer_path)
+        self.mimo_audio_tokenizer = MiMoAudioTokenizer.from_pretrained(
+            self.mimo_audio_tokenizer_path,
+            torch_dtype=torch.bfloat16,
+        )
 
-        self.mimo_audio_tokenizer.eval().bfloat16().to(self.device)
+        self.mimo_audio_tokenizer.eval().to(self.device)
         print(
             f"MiMo-Audio Tokenizer loaded in {time.monotonic() - start_loading_mimo_audio_tokenizer_time:.2f} seconds, device: {self.device}"
         )