流程开始于:
Thu, 05 Sep 2024 03:11:01 GMT
过程持续时间:
3.45 s
进度消息:
Task has been received.
USE Sequence2Txt LLM to transcription the audio
Sequence2Txt LLM file_name: temp_3.wav ...
[ERROR]too many values to unpack (expected 2)
No chunk! Done!
Expected behavior
No response
Steps to reproduce
audio file(wav) to embedding, use dashscope 'paraformer-realtime-8k-v1' asr model.
hi @mayonggang When integrating the Qianwen ASR service, an issue was encountered. It is recommended to temporarily use another provider's ASR service.
Is there an existing issue for the same bug?
Branch name
main
Commit ID
none
Other environment information
Actual behavior
流程开始于: Thu, 05 Sep 2024 03:11:01 GMT 过程持续时间: 3.45 s 进度消息: Task has been received. USE Sequence2Txt LLM to transcription the audio Sequence2Txt LLM file_name: temp_3.wav ... [ERROR]too many values to unpack (expected 2) No chunk! Done!
Expected behavior
No response
Steps to reproduce
Additional information
No response