GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
rasgaard
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
rasgaard
Model Tree
openai/whisper-large-v3-turbo
Input Modalities
Output Modalities
Supported Functionality
The 32-layer Whisper encoder contains redundant middle layers. This model removes the 6 least important layers (identified via leave-one-out ΔWER ranking), then re-aligns the pruned encoder to the original using MSE distillation on unlabelled speech — no transcriptions required.
The result is a drop-in replacement: same architecture family, same tokenizer, same decoder — just a shallower encoder.
| Language | Baseline | Zero-shot pruned | After distillation |
|---|---|---|---|
| Danish | 23.9% | 32.1% (+8.2 pp) | 27.3% (+3.4 pp) |
| English | 15.4% | 16.6% (+1.2 pp) | 16.1% (+0.7 pp) |
| German | 17.1% | 18.3% (+1.2 pp) | 18.1% (+1.0 pp) |
| French | 16.3% | 20.7% (+4.4 pp) | 18.7% (+2.5 pp) |
| Mean | +3.8 pp | +1.9 pp |
Evaluated on FLEURS test splits. Parentheses show absolute change in percentage points.
| Metric | Full model | This model |
|---|---|---|
| Encoder layers | 32 | 26 |
| Encoder parameters | 637M | 519M (−18.5%) |
| Model size (bf16) | 1543 MB | 1318 MB (−225 MB) |
| Encoder speedup | 1.00× | 1.22× |
python
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessorimport torch model = AutoModelForSpeechSeq2Seq.from_pretrained( "rasgaard/whisper-large-v3-turbo-encoder-pruned", torch_dtype=torch.bfloat16,)processor = AutoProcessor.from_pretrained( "rasgaard/whisper-large-v3-turbo-encoder-pruned")text
@misc{aagaard2026layerslessencoderpruning, title={Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery}, author={Rasmus Aagaard and Nicki Skafte Detlefsen}, year={2026}, eprint={2609.27980}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2609.27980}, }from transformers import AutoModelForSpeechSeq2Seq, AutoProcessorimport torch model = AutoModelForSpeechSeq2Seq.from_pretrained( "rasgaard/whisper-large-v3-turbo-encoder-pruned", torch_dtype=torch.bfloat16,)processor = AutoProcessor.from_pretrained( "rasgaard/whisper-large-v3-turbo-encoder-pruned")@misc{aagaard2026layerslessencoderpruning, title={Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery}, author={Rasmus Aagaard and Nicki Skafte Detlefsen}, year={2026}, eprint={2609.27980}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2609.27980}, }