From d9ce63ee39bc5ccf584910a38c0f3772736dddd6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Felix=20Sp=C3=B6ttel?=
 <1682504+fspoettel@users.noreply.github.com>
Date: Wed, 8 Feb 2023 16:29:21 +0100
Subject: [PATCH] feat: type whisper transcripts

---
 app/shared/db/schemas.py | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/app/shared/db/schemas.py b/app/shared/db/schemas.py
index 8bd5197..dc2e2d7 100644
--- a/app/shared/db/schemas.py
+++ b/app/shared/db/schemas.py
@@ -49,8 +49,20 @@ class Job(WithDbFields):
     config: Optional[JobConfig]
 
 
+class RawTranscript(BaseModel):
+    id: int
+    seek: int
+    start: float
+    end: float
+    text: str
+    tokens: List[int]
+    temperature: float
+    avg_logprob: float
+    compression_ratio: float
+    no_speech_prob: float
+
+
 class Artifact(WithDbFields):
-    # TODO: narrow type
-    data: Optional[List[Any]]
+    data: Optional[List[RawTranscript]]
     job_id: UUID
     type: ArtifactType