GoogleCloudPlatform / GoogleCloudPlatform/python-docs-samples

Speech API python client library method `streaming_recognize()` doesn't return a result with `is_final` set to True

未關閉
#12,570 1 則留言 0 個 reaction 已指派 1 人 已被 @engelke 認領 在 GitHub 檢視
priority: p2 samples triage me type: bug
主要語言
Jupyter Notebook
星號
8.1k
分支
6.7k
平均合併
4 天 2 小時
30 天內合併 PR
16

描述

## In which file did you encounter the issue?
- https://github.com/GoogleCloudPlatform/python-docs-samples/blob/main/speech/microphone/transcribe_streaming_infinite.py

## Did you change the file? If so, how?
I have changed the line 299
```
config = speech.RecognitionConfig(
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=SAMPLE_RATE,
language_code="en-US",
max_alternatives=1,
)
```
into
```
config = speech.RecognitionConfig(
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
sample_rate_hertz=SAMPLE_RATE,
language_code="ja-JP",
max_alternatives=1,
)
```

## Describe the issue
streaming_recognize() method doesn't work properly. For even when a speaker utters a simple greeting like こんにちは in a very silent environment, this method returns StreamingRecognizeResponse object with a result of is_final == False. And always returns a result with is_final set to True exactly 90 seconds later.
this doesn't happen when the language is English or Chinese.
The same thing also happens in `transcribe_streaming_infinite_v2.py`

I am not sure if this report should be post here for this seems to be more internal problem.
Appreciate any help or clues anyways.

貢獻指南

開啟貢獻指南

評估

這個 Issue 還沒有評估資料。

把新 issue 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。