IndexError: string index out of range (最後一個步驟無法生成)

[kai1040112]

Set seed to 3367266406 并行推理模式已开启 分桶处理模式已开启 实际输入的参考文本: 英文的恨有四个字母，但爱也是有四个字母。 ############ 切分文本 ############ Traceback (most recent call last): File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\gradio\routes.py", line 321, in run_predict output = await app.blocks.process_api( File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\gradio\blocks.py", line 1006, in process_api result = await self.call_function(fn_index, inputs, iterator, request) File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\gradio\blocks.py", line 859, in call_function prediction = await anyio.to_thread.run_sync( File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, *args) File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\gradio\utils.py", line 408, in async_iteration return next(iterator) File "D:\GPT-SoVITS-beta0306fix3\GPT_SoVITS\inference_webui.py", line 121, in inference for item in tts_pipeline.run(inputs): File "D:\GPT-SoVITS-beta0306fix3\runtime\lib\site-packages\torch\utils_contextlib.py", line 35, in generator_context response = gen.send(None) File "D:\GPT-SoVITS-beta0306fix3\GPT_SoVITS\TTS_infer_pack\TTS.py", line 681, in run data = self.text_preprocessor.preprocess(text, text_lang, text_split_method) File "D:\GPT-SoVITS-beta0306fix3\GPT_SoVITS\TTS_infer_pack\TextPreprocessor.py", line 57, in preprocess texts = self.pre_seg_text(text, lang, text_split_method) File "D:\GPT-SoVITS-beta0306fix3\GPT_SoVITS\TTS_infer_pack\TextPreprocessor.py", line 74, in pre_seg_text if (text[0] not in splits and len(get_first(text)) < 4): IndexError: string index out of range

[ChasonJiang]

能给出详细的测试用例吗？包括：待合成的文本、合成的语言、切分方式