Update custom model files, README, and requirements

asr_config.py

@@ -14,7 +14,7 @@ class ASRConfig(transformers.PretrainedConfig):
         attn_implementation: str = "flash_attention_2",
         model_dtype: str = "bfloat16",
         num_beams: Optional[int] = None,
-        system_prompt: str = "You are a helpful transcription assistant",
+        system_prompt: str = "",
         user_prompt: str = "Please transcribe this English audio into text: <audio>",
         encoder_dim: Optional[int] = None,
         llm_dim: Optional[int] = None,