Update custom model files, README, and requirements

asr_pipeline.py

@@ -60,6 +60,10 @@ class ASRPipeline(transformers.AutomaticSpeechRecognitionPipeline):
         return {"tokens": generated_ids, "is_last": is_last}
 
     def postprocess(self, model_outputs, **kwargs) -> dict[str, str]:
+        # Handle list of outputs (from chunking)
+        if isinstance(model_outputs, list):
+            model_outputs = model_outputs[0] if model_outputs else {}
+
         tokens = model_outputs.get("tokens")
         if tokens is None:
             return super().postprocess(model_outputs, **kwargs)