How could I integrate emotion recognition model into AutoModel with other models

[ruifengma]

Currently, according to the document, the way of using emotion model (e.g emotion2vec) is

from funasr import AutoModel

model = AutoModel(model="iic/emotion2vec_plus_large")

wav_file = f"{model.model_path}/example/test.wav"
res = model.generate(wav_file, output_dir="./outputs", granularity="utterance", extract_embedding=False)
print(res)

But what if I wish to use the model as an assistant model ( vad, spk model etc.), what should I do, or if there is any plan to add such a parameter (ser_model="iic/emotion2vec_plus_large" maybe?)