Merge branch 'dev_gzf_funasr2' into main

zhifu gao

2023-12-11 c0008fd46134d60a3a41b022bf9156cea5b145e5

 funasr/datasets/small_datasets/preprocessor.py

@@ -361,6 +361,7 @@
                    tokens = seg_tokenize(tokens, self.seg_dict)
            else:
                tokens = self.tokenizer.text2tokens(text)
                
            text_ints = self.token_id_converter.tokens2ids(tokens)
            data[self.text_name] = np.array(text_ints, dtype=np.int64)
        return data