Hugging Face's logo

nabin2004
/
AOS-qwen3-8b-narrated-adapter

Text-to-Speech
Safetensors
manim
manim-voiceover
aos
lora
sft
Model card Files
xet
 Community

AOS-qwen3-8b-narrated-adapter

Fine-tuned LoRA adapter on 400 Narrated Manim Trajectories using manim-voiceover.

Features

  • Pedagogical Audio Grounding: Synthesizes synchronized VoiceoverScene Python scripts.
  • Timing Synchronization: Generates animations bounded by run_time=tracker.duration.
  • Phonetic LaTeX: Spoken voiceover scripts express formulas verbally without raw LaTeX syntax errors.

Base Model

  • Qwen/Qwen3-8B
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Text-to-Speech
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nabin2004/AOS-qwen3-8b-narrated-adapter

Base model

Qwen/Qwen3-8B-Base
Finetuned
Qwen/Qwen3-8B
Adapter
(2135)
this model

Collection including nabin2004/AOS-qwen3-8b-narrated-adapter