🎙️ Qwen3-ASR-1.7B-EN-Medical — English Speech Recognition
1.7B Parameters
Speech to Text
English
Automatic Speech Recognition
Base model
bf16
Apache-2.0
A medical-domain English automatic speech recognition (ASR) model,
fine-tuned from Qwen/Qwen3-ASR-1.7B
on the English subset of MultiMed
mixed with Common Voice 17 English (train + validation). It outputs
cased, punctuated English text and works as a drop-in replacement for
the base model.
On MultiMed English (test) it reaches 16.50% normalized WER, essentially tied with the published MultiMed paper SOTA (16.62%). On Common Voice 17 English (test) it improves to 6.68% normalized WER vs the base model's 7.54%.
📊 Results
WER and CER on two held-out test sets — medical (in-domain) and general English (out-of-domain). All numbers are normalized (lowercase + strip punctuation), the standard protocol used by the MultiMed paper and the Open ASR Leaderboard, so they are directly comparable to other published results. "Zero-shot" is the unmodified Qwen/Qwen3-ASR-1.7B.
Test set
Samples
Zero-shot WER
Fine-tuned WER
Δ WER
Zero-shot CER
Fine-tuned CER
MultiMed English (test)
7,567
16.41
16.50
+0.09
12.60
12.45
Common Voice 17 EN (test)
16,393
7.54
6.68
-0.86
3.68
3.29
For reference, the MultiMed paper's best published result is Whisper-Small multilingual fine-tune at 16.62% WER (arXiv 2409.14074, Table 6). Both the base Qwen3-ASR and this fine-tune match that level.
The interesting story here is general English. The fine-tune actually improves on the base model's CV17 WER by 0.86 absolute points / 11% relative, while preserving medical performance. That's the opposite of catastrophic forgetting — including Common Voice in the training mix kept the base distribution intact and the medical exposure didn't hurt anything.
🧹 Reference / target normalisation
MultiMed transcripts are real-world clinical speech and inconsistent in casing and trailing punctuation. To give the model a clean, predictable target distribution we apply a small, deterministic written-form normalisation to every reference at load time, both during training and during evaluation:
Capitalise the first letter if it is lowercase.
Collapse trailing dots — any sequence of ., …, .., ... at the
end is replaced with a single ..
Append a terminal period if the sentence does not already end in
terminal punctuation (. ! ? …) or a closing bracket / quote
() ] } " ' etc.).
The exact function lives in src/evaluation/score_written_form.py of the
project repository. Concretely:
Raw reference
Normalised
the patient presented with chest pain
The patient presented with chest pain.
TAVI is indicated for severe aortic stenosis...
TAVI is indicated for severe aortic stenosis.
What is the dosage?
What is the dosage?(unchanged)
Because the same normalisation is applied to references used for the
zero-shot baseline above, the gain reported in the results table reflects the
fine-tune itself — not a metric quirk caused by mismatched references.
🚀 How to use
Install the official qwen-asr package, then load this model exactly the
same way you would load the base Qwen3-ASR:
Batch inference, automatic language detection, streaming, and vLLM serving
all work identically to the base model — see the
upstream Qwen3-ASR documentation for
details.
Concatenated and shuffled per epoch. CV17 dominates the mix at ~97.5% by clip count, which anchors general English while MultiMed steers the model toward clinical vocabulary.
Validation: MultiMed-en eval split (~2,807 clips) drives best-checkpoint selection. CV17 test stays fully held out.
Trained on a single H100. The best checkpoint was selected by validation loss.
⚠️ Limitations
Trained on MultiMed medical-domain speech (clinical consultations, surgical
procedures, patient narratives). Performance outside medical contexts is
not guaranteed to improve over the base model.
Outputs English text. Cross-lingual or code-switched audio is not
targeted.
Punctuation and casing are best-effort and inherit the inconsistencies of
the underlying transcripts (mitigated, but not eliminated, by the
normalisation step above).
Long-form clinical audio (>30s) is filtered out at training time; very
long consultations may need to be chunked at inference.
🙏 Acknowledgements
This model would not exist without the work of others. Thank you to:
The Qwen team at Alibaba Cloud for releasing
Qwen3-ASR-1.7B — the backbone of
this fine-tune — together with a clean, reproducible
SFT recipe.
Khai Le-Duc and the MultiMed authors for releasing the MultiMed
multilingual medical ASR dataset
(leduckhai/MultiMed,
paper) that made this domain-specialised
fine-tune possible.
