Downloads · 30 days
18
12% of all-time downloads
lilfugu-experimental
holotherapper/lilfugu-experimental
lilfugu-experimental is a automatic speech recognition model from holotherapper. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.
Aggressive variant of lilfugu with stronger term conversion.
All-time downloads
155
Public
Parameters
2B
4.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Model type
- qwen3_asr
- Access
- Public
- Created
- Apr 12, 2026
- Updated
- Apr 16, 2026
- SHA
- 247c5d32
Base models
Model card
From the Hugging Face model README
lilfugu-experimental
Aggressive variant of lilfugu with stronger term conversion.
This variant converts terms more aggressively — higher benchmark scores, but may over-convert in some cases. For a more conservative approach, see lilfugu.
Comparison with lilfugu
| lilfugu | lilfugu-experimental | |
|---|---|---|
| Term conversion | Conservative | Aggressive |
| DevTerm Composite | 0.6272 | 0.7648 |
| JSUT CER (general) | 10.8% | 11.9% |
Benchmarks
ADLIB (DevTerm, 247 test cases)
| Model | CER | Term Accuracy (Exact) | Composite |
|---|---|---|---|
| lilfugu-experimental | 14.6% | 68.5% | 0.7648 |
| lilfugu | 26.3% | 51.6% | 0.6272 |
| Qwen3-ASR-1.7B (base) | 41.1% | 24.6% | 0.4203 |
| Whisper large-v3-turbo | 41.9% | 20.2% | 0.3935 |
Benchmark: ADLIB — Language-aware ASR benchmark for Japanese
JSUT basic5000 (General Japanese, 300 samples)
| Model | CER |
|---|---|
| Qwen3-ASR-1.7B (base) | 10.7% |
| lilfugu | 10.8% |
| lilfugu-experimental | 11.9% |
Dataset: JSUT
Variants
| Repository | Size | Format |
|---|---|---|
| lilfugu-experimental (this) | 4.1 GB | MLX bfloat16 |
| lilfugu-experimental-8bit | 2.8 GB | MLX 8bit quantized |
| lilfugu-experimental-transformers | 4.1 GB | safetensors fp16 (CUDA/Linux) |
| lilfugu-experimental-transformers-8bit | 2.2 GB | bitsandbytes int8 (CUDA/Linux) |
| lilfugu-experimental-lora | ~49 MB | LoRA adapter |
Usage
MLX (Apple Silicon)
pip install -U mlx-audio
from mlx_audio.stt import load
model = load("holotherapper/lilfugu-experimental")
result = model.generate("audio.wav", language="Japanese")
print(result.text)
CUDA / Linux
from qwen_asr import Qwen3ASRModel
model = Qwen3ASRModel.from_pretrained("holotherapper/lilfugu-experimental-transformers")
result = model.transcribe("audio.wav")
License
Apache 2.0
- Task
- Automatic Speech Recognition
- Library
- mlx
- Type
- qwen3_asr
- License
- apache-2.0
- Languages
- ja
- Created
- Apr 12, 2026
- Updated
- Apr 16, 2026