GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
syvai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
syvai
Model Tree
danish-foundation-models/edda-v0.2-large
Input Modalities
Output Modalities
Supported Functionality
Measured end to end, encoder included, at batch size 1 on one RTX 3090 in fp16. The test used 60 clips of at most 30 s
from each test set of the open Danish ASR leaderboard.
"Identical" compares against edda's own greedy generate() output.
| test set | identical | tokens per edda pass | speed-up | edda greedy → hurtig |
|---|---|---|---|---|
| FTSpeech | 60/60 | 9.31 | 3.22× | 407 → 126 ms |
| FLEURS da_dk | 60/60 | 5.56 | 2.57× | 467 → 182 ms |
| CoRal-v3 conversation | 60/60 | 5.63 | 2.23× | 298 → 134 ms |
| CoRal-v3 read-aloud | 60/60 | 4.56 | 1.99× | 291 → 147 ms |
| Common Voice Danish | 59/60 | 5.41 | 1.91× | 218 → 114 ms |
| all | 299/300 | 5.94 | 2.39× | 336 → 140 ms |
The one clip that differs is a half-precision near-tie. Verifying a block of tokens in one pass can flip a choice between two almost equally likely tokens, compared with decoding them one at a time.
Greedy, not beam search. Edda's default decoding is beam search with 5 beams, and that is what its published WER of 8.65 uses. Hurtig reproduces edda's greedy output, which has a somewhat higher WER than 5-beam search. Use plain edda with beams if you need the last bit of accuracy, and hurtig if you need speed.
python
# pip install transformers torch safetensors huggingface_hub soundfileimport sys, soundfile as sffrom huggingface_hub import snapshot_download path = snapshot_download("syvai/edda-v0.2-large-hurtig")sys.path.insert(0, path)from hurtig import load, transcribe model, drafter, processor = load(path) # edda + drafter on CUDA in fp16audio, sr = sf.read("clip.wav", dtype="float32") # mono, 16 kHz, at most 30 sprint(transcribe(model, drafter, processor, audio, sampling_rate=sr))hurtig.spec_generate(model, drafter, mel) returns the token ids and the number of tokens accepted per edda pass.
The repo still loads as plain edda: WhisperForConditionalGeneration.from_pretrained("syvai/edda-v0.2-large-hurtig")
ignores the drafter files.
Limitations:
<|da|><|transcribe|><|notimestamps|>).hurtig.py follows z-lab/dflash's DFlash2DraftModel, adapted to Whisper:
drafter.safetensors.Training. The drafter was trained for 20k steps on edda's own greedy transcripts of 80k Danish training clips. The audio came from FTSpeech, CoRal-v3, NST, FLEURS and Common Voice train splits, in edda's training mix. It learns to predict what edda will write, not the reference transcripts. Loss is DFlash's position-decayed cross-entropy (γ = 7) plus a cross-entropy loss on the selector.
Apache License 2.0, the same as edda.
model.safetensors, config.json, generation_config.json, the tokenizer and preprocessor files) is
redistributed unchanged from danish-foundation-models/edda-v0.2-large.
Edda was trained by the Alexandra Institute within the CoRal project and released by Danish Foundation Models under the
Apache License 2.0. Its base model, openai/whisper-large-v3, is MIT-licensed.drafter.safetensors, drafter_config.json, hurtig.py) was trained by syv.ai. It is
a derivative of edda: it is initialised from edda's decoder layers and trained on edda's outputs.The training audio corpora carry their own licenses; see the respective dataset cards linked from edda's model card.
# pip install transformers torch safetensors huggingface_hub soundfileimport sys, soundfile as sffrom huggingface_hub import snapshot_download path = snapshot_download("syvai/edda-v0.2-large-hurtig")sys.path.insert(0, path)from hurtig import load, transcribe model, drafter, processor = load(path) # edda + drafter on CUDA in fp16audio, sr = sf.read("clip.wav", dtype="float32") # mono, 16 kHz, at most 30 sprint(transcribe(model, drafter, processor, audio, sampling_rate=sr))