# danish-foundation-models/edda-v0.1

Model from Hugging Face for automatic speech recognition: danish-foundation-models/edda-v0.1 · transformers

## Facts

- Type: LLM
- Task: automatic-speech-recognition
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/danish-foundation-models/edda-v0.1
- Hosting: hosted (7 files)
- Files: 7 hosted of 9 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 7 files, 1.62 GB
- Full repo upstream: 1.62 GB
- Recommended file: 1.62 GB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-danish-foundation-models-edda-v0-1/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-danish-foundation-models-edda-v0-1/download-plan)
- Per-file SHA-256: available for 7 of 7 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-danish-foundation-models-edda-v0-1/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 9
- Stars: 2
- Card completeness: 96%

## Description

External Hugging Face catalog record for danish-foundation-models/edda-v0.1. Task: automatic speech recognition. Library: transformers. Languages: da. Datasets referenced by card metadata: CoRal-project/coral-v3, alexandrainst/ftspeech, alexandrainst/nst-da, google/fleurs, mozilla-foundation/common_voice_17_0. Base model: openai/whisper-large-v3-turbo. Includes 10 model-card evaluation signals. Popularity signal at import: 9 downloads and 2 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: automatic-speech-recognition
- Library: transformers
- Base model: openai/whisper-large-v3-turbo
- Task categories: automatic-speech-recognition
- Languages: da
- Referenced datasets: CoRal-project/coral-v3, alexandrainst/ftspeech, alexandrainst/nst-da, google/fleurs, mozilla-foundation/common_voice_17_0
- Model-index entries: Edda-v0.1
- Evaluation signals: 10 model-card eval results
- File hints: 9 upstream file samples

## Evaluation Signals

- CoRal-v3 conversation (test): WER = 15.99 (Automatic Speech Recognition)
- CoRal-v3 conversation (test): CER = 9.08 (Automatic Speech Recognition)
- CoRal-v3 read-aloud (test): WER = 10.52 (Automatic Speech Recognition)
- CoRal-v3 read-aloud (test): CER = 4.12 (Automatic Speech Recognition)
- Common Voice Danish (leaderboard set: WER = 5.99 (Automatic Speech Recognition)
- Common Voice Danish (leaderboard set: CER = 1.92 (Automatic Speech Recognition)
- FLEURS da_dk (test): WER = 7.56 (Automatic Speech Recognition)
- FLEURS da_dk (test): CER = 2.95 (Automatic Speech Recognition)
- FTSpeech (test_balanced): WER = 5.95 (Automatic Speech Recognition)
- FTSpeech (test_balanced): CER = 3.28 (Automatic Speech Recognition)

## Referenced Data

- Dataset: CoRal-project/coral-v3
- Dataset: alexandrainst/ftspeech
- Dataset: alexandrainst/nst-da
- Dataset: google/fleurs
- Dataset: mozilla-foundation/common_voice_17_0

## File Hints

- .gitattributes (1.5 KB)
- README.md (7.9 KB)
- config.json (1.2 KB)
- generation_config.json (3.7 KB)
- model.safetensors (1.5 GB) LFS
- preprocessor_config.json (316 B)
- processor_config.json (410 B)
- tokenizer.json (3.7 MB)
- tokenizer_config.json (2.0 KB)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-25T16:51:28.672Z.
- Open license detected as apache-2.0.
- Model-index metadata found for Edda-v0.1.
- Model card references dataset context: CoRal-project/coral-v3, alexandrainst/ftspeech, alexandrainst/nst-da, google/fleurs.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-danish-foundation-models-edda-v0-1
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-danish-foundation-models-edda-v0-1/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-danish-foundation-models-edda-v0-1/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-danish-foundation-models-edda-v0-1/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-danish-foundation-models-edda-v0-1
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-danish-foundation-models-edda-v0-1/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-danish-foundation-models-edda-v0-1&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-danish-foundation-models-edda-v0-1/decentralized-fallbacks