[index-tts]有时候运行错误，应该怎么解决？

输入某些句子时候，可以正常运行 在输入另外一些句子时候，会有一下提示 应该怎么解决呢？显卡2080ti魔改22G tensor([[10203]], device='cuda:0', dtype=torch.int32) text_tokens shape: torch.Size([1, 1]) ['▁.'] tensor([1], device='cuda:0', dtype=torch.int32) tensor([[7919, 8193]], device='cuda:0') codes shape: torch.Size([1, 2]) Traceback (most recent call last): File "F:\anaconda3\envs\index-tts\lib\site-packages\gradio\queueing.py", line 625, in process_events response = await route_utils.call_process_api( File "F:\anaconda3\envs\index-tts\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api output = await app.get_blocks().process_api( File "F:\anaconda3\envs\index-tts\lib\site-packages\gradio\blocks.py", line 2137, in process_api result = await self.call_function( File "F:\anaconda3\envs\index-tts\lib\site-packages\gradio\blocks.py", line 1663, in call_function prediction = await anyio.to_thread.run_sync( # type: ignore File "F:\anaconda3\envs\index-tts\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "F:\anaconda3\envs\index-tts\lib\site-packages\anyio_backends_asyncio.py", line 2470, in run_sync_in_worker_thread return await future File "F:\anaconda3\envs\index-tts\lib\site-packages\anyio_backends_asyncio.py", line 967, in run result = context.run(func, args) File "F:\anaconda3\envs\index-tts\lib\site-packages\gradio\utils.py", line 890, in wrapper response = f(args, kwargs) File "F:\index-tts\webui.py", line 31, in gen_single output_path = infer(prompt, text) File "F:\index-tts\webui.py", line 27, in infer tts.infer(voice, text, outputpath) File "F:\index-tts\indextts\infer.py", line 152, in infer wav, = self.bigvgan(latent.transpose(1, 2), auto_conditioning.transpose(1, 2)) File "F:\anaconda3\envs\index-tts\lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "F:\anaconda3\envs\index-tts\lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl return forward_call(args, kwargs) File "F:\index-tts\indextts\BigVGAN\models.py", line 205, in forward x = self.conv_pre(x) File "F:\anaconda3\envs\index-tts\lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "F:\anaconda3\envs\index-tts\lib\site-packages\torch\nn\modules\module.py", line 1845, in _call_impl return inner() File "F:\anaconda3\envs\index-tts\lib\site-packages\torch\nn\modules\module.py", line 1793, in inner result = forward_call(args, **kwargs) File "F:\anaconda3\envs\index-tts\lib\site-packages\torch\nn\modules\conv.py", line 375, in forward return self._conv_forward(input, self.weight, self.bias) File "F:\anaconda3\envs\index-tts\lib\site-packages\torch\nn\modules\conv.py", line 370, in _conv_forward return F.conv1d( RuntimeError: Calculated padded input size per channel: (6). Kernel size: (7). Kernel size can't be greater than actual input size