yusufipek/dikte
1
0
Fork 0
mirror of https://github.com/yusufipk/dikte.git synced 2026-09-12 03:16:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Let OpenRouter subtitles use a chosen model instead of whisper-1

Browse Source 
A timestamped run on OpenRouter always asked openai/whisper-1 for the
segments, whatever model was picked for plain transcription. Not every
model there returns segment times, so the one to use is now its own
setting, openrouter_subtitle_model, shown in the speech-to-text box only
when OpenRouter is the provider. Empty keeps the old whisper-1 fallback.

Target carries the choice as subtitle_model and timestamp_model() reads
it; the other providers are unchanged.
This commit is contained in:
yusufipek
2026-09-02 12:41:43 +03:00
parent 310ef8d7cf
commit 6e307bd8d0
7 changed files with 98 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
dikte/i18n.py
+5
View File
@@ -228,6 +228,11 @@ TR = {
"Transcript cleanup": "Transkripti temizleme",
"API key": "API anahtarı",
"Model": "Model",
"Subtitle model": "Altyazı modeli",
"The model a timestamped run (subtitles) asks for. Not every model on "
"OpenRouter returns segment times; empty means openai/whisper-1.":
"Zaman damgalı bir çeviride (altyazı) istenen model. OpenRouter'daki her "
"model segment zamanı döndürmez; boşsa openai/whisper-1 kullanılır.",
"Provider": "Sağlayıcı",
"sk-… (falls back to OPENAI_API_KEY)": "sk-… (boşsa OPENAI_API_KEY kullanılır)",
"gsk_… (falls back to GROQ_API_KEY)": "gsk_… (boşsa GROQ_API_KEY kullanılır)",