v3.5.0 #108
MaKTaiL
announced in
Announcements
v3.5.0
#108
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
🚀 Major Update
Model Transition
New Features
--token-statsflag to show real-time token usage during translation and transcription--no-contextflag to disable context preservation between batches (reduces token usage)preserve_contextparameter (default:True) maintains context for improved continuityModel Configuration Enhancements
📋 Parameter Changes
API Changes
model_name:"gemini-2.5-flash"→"gemini-3.5-flash"batch_size:300→1000New Parameters
token_stats: Show token usage information (default:False)preserve_context: Preserve context between batches (default:True)🔧 Technical Improvements
Error Handling
ValueErrorinstead of continuingPerformance Optimizations
gemini-3.1-flash-liteCode Quality
main.pyfor improved readability📦 Dependencies
Updated minimum versions:
google-genai:>= 1.56.0→>= 2.6.0json-repair:>= 0.54.3→>= 0.59.10audioop-ltsversion constraintPython Version Support
📚 Documentation
Full Changelog: v3.0.1...v3.5.0
This discussion was created from the release v3.5.0.
All reactions