Downloads · 30 days
0
Usin2705/dta_asa
dta_asa is a machine learning model from Usin2705. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Weights for the DTA Finnish speaking scorer (M-CASA). Deployment artefact, not a general model release. Loaded by the inference/ package in aalto-speech/dta-server; it will not load with plain transformers because the…
Downloads · 30 days
0
Access
Public
Updated Jul 31, 2026
Repo size
15.9 GB
Likes
0
Public
Click a slice to open those files.
.safetensors15.8 GB · 100%
From the Hugging Face model README
Weights for the DTA Finnish speaking scorer (M-CASA). Deployment artefact, not a general
model release. Loaded by the inference/ package in aalto-speech/dta-server; it will not
load with plain transformers because the architecture lives in that package.
| checkpoint | finnish-v3_le40_mcasa_noac_eqcap2x_ttsfluall3_s2022 |
| test RMSE (98 held-out DTA recordings, calibrated) | 0.3854 |
| reportable CEFR range | 1.14 – 3.50 |
scorer/model.safetensors trained checkpoint (complete state dict)
whisper_finnish_v3/ Finnish ASR fine-tune, also the acoustic backbone. Whisper-medium.
qwen_base/ Qwen3.5-2B base (Apache-2.0)
assets/ task catalogue, calibrator and model card for THIS checkpoint
assets/ is uploaded alongside the weights on purpose. The container image also ships a copy,
and the two must agree — dta_scorer.config.check_weights_match_assets() refuses to start if
the mounted weights do not match the image's model card.
The calibrated score is clipped to [1.14, 3.50]; the model cannot certify B2 or
above. Trained on Finnish L2 speech for the specific task prompts in assets/tasks.json.
See assets/model_card.json for full provenance, measured metrics and known limits.