GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
thorhojhus
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
thorhojhus
Model Tree
openai/whisper-large-v3-turbo
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline model_id = "thorh/whisper-large-v3-turbo-danish"device = "cuda:0" if torch.cuda.is_available() else "cpu"dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32 processor = AutoProcessor.from_pretrained(model_id)model = AutoModelForSpeechSeq2Seq.from_pretrained( model_id, dtype=dtype, low_cpu_mem_usage=True,).to(device) transcribe = pipeline( "automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, dtype=dtype, device=device,) result = transcribe( "audio.wav", generate_kwargs={"language": "da", "task": "transcribe", "num_beams": 1},)print(result["text"])Training used the Danish portions of CoRal v3, Common Voice 26.0, FLEURS,
FTSpeech and NST together with filtered pseudo-labelled data. The pseudo-labels
were generated with openai/whisper-large-v3
and confidence-filtered before use.
Targets retained their original casing, punctuation and numeral style. Audio augmentation, SpecAugment and synthetic no-speech examples were included. The data design was inspired by the weak-supervision and no-speech principles in the original Whisper paper.
| Setting | Value |
|---|---|
| Steps | 200,000 |
| Optimizer | Muon for hidden matrices; AdamW for remaining parameters |
| Peak learning rate | Muon 5e-6; AdamW 2.5e-6 |
| Weight decay | 0.01 |
| Schedule | 1,000-step warmup, stable to 50,000, linear decay to 10% at 200,000 |
| EMA | 0.9999 per step |
| Precision | BF16 parameters, FP8 hidden forward GEMMs, compensated FP32 optimizer updates |
| Maximum training segment | 30 seconds |
| Training hardware | One NVIDIA GeForce RTX 4090 |
| Active wall time | Approximately 56 hours |
The following figures are cumulative audio sampled during training. They include repeated sampling and are not unique dataset durations.
| Source | Hours seen |
|---|---|
| CoRal conversation | 485.45 |
| CoRal read-aloud | 894.45 |
| Common Voice Danish | 72.63 |
| FLEURS Danish | 74.06 |
| FTSpeech | 1,469.10 |
| NST Danish | 712.01 |
| Pseudo-labelled data | 9,200.04 |
| Total | 12,907.73 |
Additional recipe details are recorded in training_recipe.json.
The checkpoint was evaluated against the public Danish ASR Leaderboard protocol using greedy Danish transcription. Short clips used standard decoding; clips over 30 seconds used timestamped sequential long-form decoding. The leaderboard normalizer was applied, including Danish numeral normalization.
| Test set | Samples | WER (%) | CER (%) |
|---|---|---|---|
| CoRal conversation | 8,438 | 20.05 | 11.92 |
| CoRal read-aloud | 9,122 | 12.93 | 4.80 |
Common Voice (cv17_da) | 2,756 | 8.24 | 2.65 |
FLEURS da_dk | 930 |
Exact revisions and decoding settings are recorded in training_recipe.json.
The model weights are released under the MIT License. Training data are not
redistributed and remain subject to their source terms. See
THIRD_PARTY_NOTICES.md.
bibtex
@article{radford2022robust, title={Robust Speech Recognition via Large-Scale Weak Supervision}, author={Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya}, journal={arXiv preprint arXiv:2212.04356}, year={2022}}| 8.95 |
| 3.65 |
FTSpeech test_balanced | 5,534 | 7.39 | 4.19 |
| Unweighted domain mean | 26,780 | 11.51 | 5.44 |