Downloads · 30 days
0
monica
datumsteve/monica
monica is a audio classification model from datumsteve. Use it for the audio classification task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Trained decision heads for monica, a local non-generative audio-sentiment service. Frozen Gemma 4 E2B audio tower + these compact heads produce calibrated probabilities for typed questions (noul / choice / score) over…
Access
Public
Updated Sep 23, 2026
Repo size
72 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt72 MB · 100%
At a glance
- Task
- Audio Classification
- License
- apache-2.0
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 04bf2e02
Base models
Model card
From the Hugging Face model README
monica — System One audio-sentiment heads
Trained decision heads for monica, a local non-generative audio-sentiment service. Frozen Gemma 4 E2B audio tower + these compact heads produce calibrated probabilities for typed questions (noul / choice / score) over one shared audio encoding. No transcription, no generated tokens.
Code/server live in a GitHub repository (private for now; code released alongside this card later). The base model is separate: hf download google/gemma-4-E2B-it --local-dir data/models/gemma-4-E2B-it (~10 GB, Apache-2.0). This repo provides only the trained heads and artifacts:
Contents
| file | what |
|---|---|
models/head-cremad.pt | question encoder + window-attention decision heads (80 MB), trained on CREMA-D, speaker-independent splits |
models/calibration.json | per-question-type temperature scaling |
data/selected_layers.json | audio-tower layer selection (3, 4, 9, 10) |
bench/eval_results.json | full evaluation (acc, AUC, ECE, Brier, RPS, robustness, latency) |
bench/bench_results.json | latency / cold-start / memory benchmark |
bench/options_comparison.json | compact question encoder vs Gemma text trunk |
EVALUATION.md, LICENSES.md | evaluation protocol and data/model licenses |
Key numbers (CREMA-D, speaker-independent)
- noul seen words: acc 0.873, AUC 0.850, ECE 0.069; unseen words 0.839 / 0.803 / 0.037
- 6-way emotion choice: acc 0.591 (chance 0.167), macro-F1 0.584, ECE 0.101
- score level-MAE 0.50–0.62 (trained scales)
- latency (M3 Ultra, warm): ~150–200 ms per request incl. encode; RTF 0.006 at 30 s audio
- warm encode: 30 s audio in ~120 ms, once per request regardless of question count (0–64)
Usage
See the GitHub repo README for the /v1/systemone request format. Quick start:
git clone https://github.com/nunez/monica && cd monica
uv pip install -e ".[dev]" # or pip install -r requirements.txt
# point MONICA_BASE_MODEL at a local Gemma 4 E2B checkout
MONICA_BASE_MODEL=/path/to/gemma-4-E2B-it \
python -m uvicorn monica.server:app --host 0.0.0.0 --port 8910
License
Code Apache-2.0. Base model Google Gemma Terms of Use (Apache-2.0). CREMA-D: ODbL/attribution. RAVDESS: research-only (CC BY-NC-SA 4.0) — benchmark only, never trained on.
- Task
- Audio Classification
- License
- apache-2.0
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026