Update README.md

README.md

@@ -58,7 +58,6 @@ response = model.generate(
     num_beams=1,
     # temperature=0.4,
     # top_p=0.9,
-    # streamer=streamer # supports TextIteratorStreamer
 )
 print(response)
 ```
@@ -66,15 +65,15 @@ print(response)
 - wav_path (`str`) -- Path to the audio file (format = wav, flac, mp3, etc as long as `soundfile.read` supports)
 - prompt (`str`) -- Text input to the model
 - prompt_pattern (`str`) -- Chat template that is augmented with special tokens, and it must be set the same as one during training
-- max_length (`int`, *optional*, defaults to 150)
+- max_new_tokens (`int`, *optional*, defaults to 1024)
 - num_beams (`int`, *optional*, defaults to 4)
 - do_sample (`bool`, *optional*, defaults to True)
-- min_length (`int`, *optional*, defaults to 1)
 - top_p (`float`, *optional*, defaults to 0.9)
 - repetition_penalty (`float`, *optional*, defaults to 1.0),
 - length_penalty (`float`, *optional*, defaults to 1.0),
 - temperature (`float`, *optional*, defaults to 1.0),
-- streamer (`TextIteratorStreamer`, *optional*, defaults to `None`) -- this allows streaming output
+
+This is also `model.generate_stream()` for streaming generation. Please refer to `modeling_typhoonaudio.py` for this function.
 
 ## Evaluation Results
 More information is provided in our [technical report](https://arxiv.org/abs/2409.10999).