adolforeyna/whisper-translation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update history with multi-language phase

Browse Source
This commit is contained in:
Adolfo Reyna
2026-02-26 21:18:48 -05:00
parent 3166d6e7d5
commit d27543022d
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
history.md
View File

@@ -39,3 +39,10 @@ The project now features a high-performance, Apple Silicon-optimized pipeline th
2. Transcribes using **MLX-Whisper (small.en)**. 2. Transcribes using **MLX-Whisper (small.en)**.
3. Translates using **MarianMT (EN-ES)**. 3. Translates using **MarianMT (EN-ES)**.
4. Operates entirely locally with hardware acceleration. 4. Operates entirely locally with hardware acceleration.
## Phase 5: Simultaneous Multi-Language Translation
- **Goal:** Provide translations in Spanish, French, and Arabic at the same time.
- **Approach:**
- Refactored the script to support a dictionary of multiple `MarianMT` models.
- Each transcribed English segment is passed through each loaded translation engine sequentially.
- **Performance on M2:** Loading 3-4 specialized models + Whisper is highly efficient, using ~1.5GB of RAM and providing near-instant results.