karna-large
A 217M-parameter Khmer + English CTC speech recogniser, made by structured pruning of
Meta's Omnilingual ASR omniASR_CTC_1B to about 80% encoder sparsity. It is the Large size of a pair,
named after DiariZen's Base-s80 / Large-s80 pruned WavLM models. The other size is
Netra-Lab/karna-base.
Code: github.com/netra-ai-lab/Karna, with the karna inference package and the full training recipe.
Results
Test sets; greedy CTC decoding, no language model. CER for Khmer, WER for English, in %. Lower is better.
| Model | Params | GMAC / s audio | DDD (km) | FLEURS-km | FLEURS-en | LibriSpeech test-clean | LibriSpeech test-other |
|---|---|---|---|---|---|---|---|
omniASR_CTC_1B (stock) |
975M | 50.3 | 5.95 | 11.26 | 12.38 | 4.40 | 8.87 |
| Fine-tuned 1B (teacher) | 975M | 50.3 | 1.22 | 7.77 | 12.01 | 3.54 | 7.96 |
| karna-large | 217M | 12.9 | 1.33 | 10.20 | 18.15 | 5.44 | 12.98 |
- Khmer: on DDD it is within 0.11 points of its unpruned fine-tuned teacher, and its error is less than a quarter of the stock model's.
- English: it keeps much less of its teacher's accuracy, with about 1.5β2Γ the teacher's WER, and is behind the stock model.
- Version: this is v2. The first release (204M; DDD 1.77, test-clean 6.07) is at revision
593366493e; v2 improves every test set. - In-domain test sets: FLEURS-km and FLEURS-en train are in the training mix, so their test sets are in-domain.

Inference time for one 60 s utterance (batch 1, bf16, median of 20 runs), at 0% sparsity (the fine-tuned teacher) and about 80% (Karna).
Architecture

The model, reading upwards, with one transformer layer opened up: 16 kHz audio, a feature extractor of 7 convolutional layers giving one frame every 20 ms, a convolutional position encoder added back to the frames, 48 pre-LayerNorm transformer layers of width 1,280, a final LayerNorm and a CTC head over 9,812 characters. Every attention head and every FFN unit has its own Hard Concrete gate z. The cells in the opened layer are layer 12 of karna-large: 11 of 16 heads and 3,788 of 5,120 FFN units kept; which ones are kept is schematic.

What is pruned, shown for karna-large: whole attention heads (MHA) and FFN units are removed from every transformer layer, and the CNN front end is kept. Each cell is a quarter of a layer's heads or units.
- Base: a wav2vec2-style CTC encoder with Omnilingual's 9,812-entry character vocabulary, which covers Khmer and Latin script.
- Pruned parts: per-layer attention heads and FFN units, so every layer has its own width.
config.jsonlists the exactnum_headsandffn_dims; the encoder has 205M parameters, 21% of the 1B's 962M. - Unchanged parts: the CNN feature extractor and the output layer.
- Loading: the layer widths are non-uniform, so fairseq2 /
omnilingual-asrcannot load it. Use thekarnapackage (see Usage) or the code bundled in this repo.
How it was made
The recipe follows Fine-tune Before Structured Pruning (arXiv 2505.24111), with the pruning method of DPHuBERT (arXiv 2305.17651) as used in DiariZen.
- Fine-tune (62k steps, about one pass over the mix). Train
omniASR_CTC_1Bwith CTC on the training mix. The result is the teacher. The first release's teacher, fine-tuned for 6k steps, is omniASR-CTC-1B-km-en. - Prune (12k steps). Hard Concrete L0 gates sit on the attention heads and FFN units. An augmented-Lagrangian constraint ramps the target sparsity to 80% over the first 6k steps. The pruned model is distilled to the teacher with an L1 β cosine loss on hidden states at layers 12, 24, 36 and 48.
- Cut. Remove the pruned units for good.
- Distil (5k steps). Keep the mask frozen and continue the layer distillation.
- Recover (24k steps). Train with CTC plus a frame-level KL divergence to the teacher's output distribution (temperature 1, weight 1).
Training mix, 50/50 by language:
- Khmer: DDD train and FLEURS-km train.
- English: LibriSpeech train-clean-100 + 360 + other-500 (961 h) and FLEURS-en train.
- FLEURS is fixed at 20% of each language's audio.
Usage
pip install git+https://github.com/netra-ai-lab/Karna
import karna
asr = karna.load_model("karna-large") # downloads this repo's weights once
print(asr.transcribe("audio.wav"))
print(asr.transcribe(["a.wav", "b.flac"]))
karna transcribe audio.wav --model karna-large
Without installing the package, the code bundled in this repo also works:
huggingface-cli download Netra-Lab/karna-large --local-dir karna-large
pip install torch torchaudio soundfile safetensors
python karna-large/inference.py audio.wav
Audio of any sample rate is accepted; it is mixed to mono and resampled to 16 kHz. Output text is in the Omnilingual character set: lowercase, with no Khmer punctuation.
Files
| File | Contents |
|---|---|
model.safetensors |
weights |
config.json |
architecture, including per-layer num_heads and ffn_dims |
vocab.json |
the Omnilingual character vocabulary, in id order |
omniprune/ |
model and text code (model.py, hardconcrete.py, text.py) |
inference.py |
load and transcribe |
The released files reproduce the training checkpoint's logits exactly: the maximum difference is 0.
License and attribution
- Weights: derived from Meta's Omnilingual ASR
omniASR_CTC_1B(Apache 2.0) and released under Apache 2.0. omniprune/hardconcrete.py: ported from DiariZen (MIT), itself derived from DPHuBERT and FLOP.
- Downloads last month
- 170