Upload asr_pipeline.py with huggingface_hub

asr_pipeline.py

@@ -521,19 +521,12 @@ class ASRPipeline(transformers.AutomaticSpeechRecognitionPipeline):
         Returns:
             Dict with 'text' key containing transcription
         """
-        # DEBUG: Track which code path we're using
-        import sys
-        print(f"[DEBUG postprocess] type(model_outputs)={type(model_outputs).__name__}", file=sys.stderr)
-
         # Handle list of outputs (from chunking)
         if isinstance(model_outputs, list):
-            print(f"[DEBUG postprocess] list len={len(model_outputs)}", file=sys.stderr)
             model_outputs = model_outputs[0] if model_outputs else {}
 
         tokens = model_outputs.get("tokens")
-        print(f"[DEBUG postprocess] tokens is None: {tokens is None}", file=sys.stderr)
         if tokens is None:
-            print("[DEBUG postprocess] FALLING BACK TO SUPER", file=sys.stderr)
             return super().postprocess(model_outputs, **kwargs)
 
         if torch.is_tensor(tokens):
@@ -544,10 +537,8 @@ class ASRPipeline(transformers.AutomaticSpeechRecognitionPipeline):
         text = self.tokenizer.decode(tokens, skip_special_tokens=True).strip()
         # Strip <think>...</think> tags (Qwen3 doesn't respect /no_think prompt)
         text = re.sub(r"<think>.*?</think>\s*", "", text, flags=re.DOTALL).strip()
-        print(f"[DEBUG postprocess] BEFORE truncation: {len(text.split())} words", file=sys.stderr)
         # Post-process prediction
         text = self._post_process_prediction(text)
-        print(f"[DEBUG postprocess] AFTER truncation: {len(text.split())} words", file=sys.stderr)
         return {"text": text}
 
     # Known hallucination patterns that should be deleted entirely