You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When setting stream=True with a low stream_batch (assume 1 or 2), even though it decreases latency to first audio chunk by a lot (~150ms on 4090), the audio is very noisy. I tried concatenate all generated audio chunks and play them together after stream finished, the noise still persisted. This is also true even when stream_batch is default (24), I can hear that the point between two concatenated audio chunks have a tiny distortion. Is this a fixable issue? thanks.
When setting stream=True with a low stream_batch (assume 1 or 2), even though it decreases latency to first audio chunk by a lot (~150ms on 4090), the audio is very noisy. I tried concatenate all generated audio chunks and play them together after stream finished, the noise still persisted. This is also true even when stream_batch is default (24), I can hear that the point between two concatenated audio chunks have a tiny distortion. Is this a fixable issue? thanks.
在流式输出时把stream_batch降到1或者2时可以减少很多latency,但是音质受到很大音响,播放音频时有很大的、持续的电流声,音调也比非流式输出时要低。另外,即使用default batch size 24,我仍然可以在音频与音频连接处听到一些杂音,请问这个问题是否可以解决?是什么原因引起的?谢谢。
ChatTTS version:0.2.1
The text was updated successfully, but these errors were encountered: