Skip to content

말하지 않는 경우 환각 생기는 문제 해결 #116

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Dryeyesyndrome merged 1 commit into from
Dec 6, 2025
Merged

말하지 않는 경우 환각 생기는 문제 해결 #116

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Sumdays/app/src/main/java/com/example/sumdays/network/ApiClient.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ import retrofit2.converter.gson.GsonConverterFactory
import java.util.concurrent.TimeUnit

object ApiClient {
const val BASE_URL = "http://172.30.1.51:3000/"
const val BASE_URL = "http://192.168.0.78:3000/"
//폰에서 실행하려면 서버를 돌리는 컴퓨터의 IP를 여기 적어야 함

// OkHttp 로깅 + 타임아웃 설정
Expand Down
10 changes: 9 additions & 1 deletion sumdays-backend/ai/services/stt/stt_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,11 +18,19 @@ def transcribe(self, audio_file, language: str = "ko") -> str:
model=self.model,
file=buffer,
language=language,
response_format="verbose_json",
)

# check if file has no speech
if hasattr(result, 'segments') and result.segments:
avg_no_speech_prob = sum(s.no_speech_prob for s in result.segments) / len(result.segments)
if avg_no_speech_prob > 0.75:
return ""

# filter hallucination manually
temp_filter = [
"MBC 뉴스",
"시청해 주셔서",
"시청해",
"구독",
"고맙습니다."
]
Expand Down
Loading