Downloads · 30 days
13
7% of all-time downloads
Qlerqly/griot-nano-1-onnx
griot-nano-1-onnx is a automatic speech recognition model from Qlerqly. Use it when you need speech turned into text. It is set up for onnx. The card lists the license as cc-by-nc-sa-4.0.
This is the unquantized FP32 ONNX Runtime distribution of Qlerqly/griot-nano-1. It contains the same 153M-parameter Conformer CTC acoustic model and is intended for local CPU transcription without PyTorch.
Downloads · 30 days
13
7% of all-time downloads
All-time downloads
180
Public
Repo size
633 MB
Likes
0
Public
Click a slice to open those files.
.onnx633 MB · 100%
From the Hugging Face model README
This is the unquantized FP32 ONNX Runtime distribution of Qlerqly/griot-nano-1. It contains the same 153M-parameter Conformer CTC acoustic model and is intended for local CPU transcription without PyTorch.
uvx --from huggingface-hub hf download Qlerqly/griot-nano-1-onnx \
--local-dir griot-nano-1-onnx
cd griot-nano-1-onnx
uv run --with-requirements requirements.txt python inference.py \
--model-dir . --audio recording.wav
# Live microphone transcription
uv run --with-requirements requirements.txt python inference.py \
--model-dir . --live
Use --threads N to control ONNX Runtime CPU threads.
For best contextual accuracy, we encourage using this runtime together with Qlerqly/griot-nano-1-kenlm. It adds n-gram beam-search guidance without another neural network, keeping the overhead low relative to neural language-model rescoring.
# From the directory containing griot-nano-1-onnx
uvx --from huggingface-hub hf download Qlerqly/griot-nano-1-kenlm \
--local-dir griot-nano-1-kenlm
cd griot-nano-1-onnx
uv run --with-requirements requirements-kenlm.txt python inference.py \
--model-dir . --audio recording.wav \
--kenlm ../griot-nano-1-kenlm/multilingual.arpa --beam-width 25
This runs ONNX Runtime and KenLM as one CPU transcription pipeline. The
suggested starting values are beam width 25, LM weight 0.5, and word
insertion bonus 1.0; override the latter two with --lm-alpha and --lm-beta.
These are the canonical model's raw greedy-CTC results. The exporter performs a
numerical PyTorch-versus-ONNX check recorded in onnx_verification.json.
| Language | Samples | CER | WER |
|---|---|---|---|
| ak | 21,435 | 19.27% | 41.67% |
| dag | 5,307 | 7.04% | 23.75% |
| ee | 6,820 | 9.66% | 30.76% |
| en | 56,364 | 12.91% | 26.05% |
| ga | 9,621 | 8.14% | 15.83% |
| Combined | 99,547 | 13.66% | 29.19% |
CPUExecutionProviderThis runtime uses the same weights, training sources, and license as the canonical model. See ATTRIBUTIONS.md for the complete source and license record.