流式生成音频报错

[6131548]

生成音频时，勾选Stream Mode，服务报
Traceback (most recent call last):
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\queueing.py", line 624, in process_events
response = await route_utils.call_process_api(
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\route_utils.py", line 323, in call_process_api
output = await app.get_blocks().process_api(
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\blocks.py", line 2018, in process_api
result = await self.call_function(
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\blocks.py", line 1579, in call_function
prediction = await utils.async_iteration(iterator)
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\utils.py", line 691, in async_iteration
return await anext(iterator)
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\utils.py", line 685, in anext
return await anyio.to_thread.run_sync(
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\anyio_backends_asyncio.py", line 2441, in run_sync_in_worker_thread
return await future
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\anyio_backends_asyncio.py", line 943, in run
result = context.run(func, *args)
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\utils.py", line 668, in run_sync_iterator_async
return next(iterator)
File "D:\tts\ChatTTSPlus-windows\venv\lib\site-packages\gradio\utils.py", line 829, in gen_wrapper
response = next(iterator)
File "D:\tts\ChatTTSPlus-windows\webui.py", line 163, in generate_audio
for gen in wav_gen:
File "D:\tts\ChatTTSPlus-windows\chattts_plus\pipelines\chattts_plus_pipeline.py", line 451, in _infer
if b > wavs.shape[1]:
AttributeError: 'list' object has no attribute 'shape'

[liulianzhu]

这个问题在TTS里面也有，是因为生成的音频是 单通道， 而你转换的时候是需要双通道，将模型推理得到的音频复制一份作为第二通道就可以了。

[liulianzhu]

另外想请教下你用的是什么环境，我的环境报下面的错误：
WARNING:ChatTTSPlusPipeline:使用空的 speaker embedding
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/gradio/queueing.py", line 625, in process_events
response = await route_utils.call_process_api(
File "/usr/local/lib/python3.10/dist-packages/gradio/route_utils.py", line 322, in call_process_api
output = await app.get_blocks().process_api(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 2108, in process_api
result = await self.call_function(
File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1667, in call_function
prediction = await utils.async_iteration(iterator)
File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 735, in async_iteration
return await anext(iterator)
File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 729, in anext
return await anyio.to_thread.run_sync(
File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 2461, in run_sync_in_worker_thread
return await future
File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 962, in run
result = context.run(func, *args)
File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 712, in run_sync_iterator_async
return next(iterator)
File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 873, in gen_wrapper
response = next(iterator)
File "/workspace/ChatTTSPlus/webui.py", line 150, in generate_audio
wav_gen = pipe.infer(
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/workspace/ChatTTSPlus/chattts_plus/pipelines/chattts_plus_pipeline.py", line 550, in infer
speaker_emb = torch.zeros((1, self.cfg.spk_emb_dim),
File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 355, in getattr
self._format_and_raise(
File "/usr/local/lib/python3.10/dist-packages/omegaconf/base.py", line 231, in _format_and_raise
format_and_raise(
File "/usr/local/lib/python3.10/dist-packages/omegaconf/_utils.py", line 899, in format_and_raise
_raise(ex, cause)
File "/usr/local/lib/python3.10/dist-packages/omegaconf/_utils.py", line 797, in _raise
raise ex.with_traceback(sys.exc_info()[2]) # set env var OC_CAUSE=1 for full trace
File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 351, in getattr
return self._get_impl(
File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 442, in _get_impl
node = self._get_child(
File "/usr/local/lib/python3.10/dist-packages/omegaconf/basecontainer.py", line 73, in _get_child
child = self._get_node(
File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 480, in _get_node
raise ConfigKeyError(f"Missing key {key!s}")
omegaconf.errors.ConfigAttributeError: Missing key spk_emb_dim
full_key: spk_emb_dim
object_type=dict

我用的是nvidia的docker镜像 nvcr.io/nvidia/tensorrt:24.10-py3， 进去之后直接用pip install -r requiement.txt 。
之后就直接 python webui.py --cfg configs/infer/chattts_plus.yaml。
这样起来后，就报上面的错误。

[liulianzhu]

另外想请教下你用的是什么环境，我的环境报下面的错误： WARNING:ChatTTSPlusPipeline:使用空的 speaker embedding Traceback (most recent call last): File "/usr/local/lib/python3.10/dist-packages/gradio/queueing.py", line 625, in process_events response = await route_utils.call_process_api( File "/usr/local/lib/python3.10/dist-packages/gradio/route_utils.py", line 322, in call_process_api output = await app.get_blocks().process_api( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 2108, in process_api result = await self.call_function( File "/usr/local/lib/python3.10/dist-packages/gradio/blocks.py", line 1667, in call_function prediction = await utils.async_iteration(iterator) File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 735, in async_iteration return await anext(iterator) File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 729, in anext return await anyio.to_thread.run_sync( File "/usr/local/lib/python3.10/dist-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 2461, in run_sync_in_worker_thread return await future File "/usr/local/lib/python3.10/dist-packages/anyio/_backends/_asyncio.py", line 962, in run result = context.run(func, *args) File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 712, in run_sync_iterator_async return next(iterator) File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 873, in gen_wrapper response = next(iterator) File "/workspace/ChatTTSPlus/webui.py", line 150, in generate_audio wav_gen = pipe.infer( File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "/workspace/ChatTTSPlus/chattts_plus/pipelines/chattts_plus_pipeline.py", line 550, in infer speaker_emb = torch.zeros((1, self.cfg.spk_emb_dim), File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 355, in getattr self._format_and_raise( File "/usr/local/lib/python3.10/dist-packages/omegaconf/base.py", line 231, in _format_and_raise format_and_raise( File "/usr/local/lib/python3.10/dist-packages/omegaconf/_utils.py", line 899, in format_and_raise _raise(ex, cause) File "/usr/local/lib/python3.10/dist-packages/omegaconf/_utils.py", line 797, in _raise raise ex.with_traceback(sys.exc_info()[2]) # set env var OC_CAUSE=1 for full trace File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 351, in getattr return self._get_impl( File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 442, in _get_impl node = self._get_child( File "/usr/local/lib/python3.10/dist-packages/omegaconf/basecontainer.py", line 73, in _get_child child = self._get_node( File "/usr/local/lib/python3.10/dist-packages/omegaconf/dictconfig.py", line 480, in _get_node raise ConfigKeyError(f"Missing key {key!s}") omegaconf.errors.ConfigAttributeError: Missing key spk_emb_dim full_key: spk_emb_dim object_type=dict

我用的是nvidia的docker镜像 nvcr.io/nvidia/tensorrt:24.10-py3， 进去之后直接用pip install -r requiement.txt 。 之后就直接 python webui.py --cfg configs/infer/chattts_plus.yaml。 这样起来后，就报上面的错误。

感觉是配置文件少了 spk_emb_dim 导致的。

[warmshao]

我在windows上测试没问题，如果你们自己在容器安装的话，我用的tensorrt是 10.2.0.post1

[warmshao]

CUDA12.2

[liulianzhu]

CUDA12.2

我看了代码，这块地方的配置 在配置文件中应该没有的啊。
配置文件是chattts_plus.yaml 吧 ？

[warmshao]

CUDA12.2

我看了代码，这块地方的配置 在配置文件中应该没有的啊。 配置文件是chattts_plus.yaml 吧 ？

@yuanyuan1-max 帮看一下，你的pr是不是少了这个参数

[yuanyuan1-max]

已提交pr添加spk_emb_dim参数。根据维度填写即可。

[zyb8543d]

这个项目流式 首包响应时间多少额，有人知道吗