Downloads · 30 days
29
36% of all-time downloads
manassehzw/sna-qwen-3-asr-1.7b
sna-qwen-3-asr-1.7b is a automatic speech recognition model from manassehzw. Use it when you need speech turned into text. It is set up for qwen-asr. The card lists the license as apache-2.0.
Shona Qwen3-ASR 1.7B is a Shona (sna) automatic speech recognition model fine-tuned from Qwen/Qwen3-ASR-1.7B on manassehzw/sna-dataset-annotated.
Downloads · 30 days
29
36% of all-time downloads
All-time downloads
81
Public
Parameters
2B
4.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors4.1 GB · 100%
From the Hugging Face model README
Shona Qwen3-ASR 1.7B is a Shona (sna) automatic speech recognition model
fine-tuned from Qwen/Qwen3-ASR-1.7B
on manassehzw/sna-dataset-annotated.
This release contains checkpoint 760 from run 20260803T140000Z. It was selected
by generated validation WER and occurs at approximately two epochs. Qwen3-ASR
adapted rapidly to Shona and substantially outperformed its zero-shot behavior on
the project dataset. Evaluation on FLEURS also revealed a meaningful domain and
speaker-generalization gap, so the in-domain score should not be treated as a
universal Shona ASR result.
Qwen/Qwen3-ASR-1.7B7278e1e70fe206f11671096ffdd38061171dd6e5manassehzw/sna-dataset-annotatedf91b1a79cbac15520d3c808b56e5192bf903f28020260803T140000Zcheckpoint-7601.996qwen-asr==0.0.6, Transformers, PyTorchText for the project evaluations was normalized with Unicode NFKC, case folding, punctuation and symbol removal, and whitespace collapse.
| Evaluation | Checkpoint | Examples | WER | CER |
|---|---|---|---|---|
| In-domain validation generation probe | 760 | 256 | 25.20% | 5.08% |
| Full in-domain test set | 855 | 1,565 | 25.51% | 4.97% |
PazaBench v2 / FLEURS sn_zw test | 855 | 925 | 52.85% | 13.57% |
| Zero-shot base model, full in-domain test set | base | 1,565 | 106.58% | 31.64% |
The full-test and FLEURS numbers are included as nearby-run context and were measured on checkpoint 855, not the released checkpoint. Checkpoints 760 and 855 were effectively tied on the 256-example generation probe: 25.198% versus 25.215% WER, a difference of one word error. A full external evaluation of checkpoint 760 has not yet been recorded.
2e-50.17747Install the official Qwen ASR package:
pip install -U qwen-asr
import torch
from qwen_asr import Qwen3ASRModel
model = Qwen3ASRModel.from_pretrained(
"manassehzw/sna-qwen-asr-1.7b",
dtype=torch.bfloat16,
device_map="cuda:0",
max_inference_batch_size=16,
max_new_tokens=256,
)
results = model.transcribe(audio="sample.wav", language=None)
print(results[0].text)
The recorded evaluations used language=None. Although the fine-tuning targets
identify the output as Shona, Shona was not in the base model's original list of
supported language arguments, so automatic language handling is the tested path.
The model is released under Apache-2.0, matching the base Qwen3-ASR model.