Automatic Speech Recognition
Transformers
Safetensors
English
qwen3_asr
speech
qwen3-asr
qwen
english
fine-tuned
medical
multimed
common-voice
Eval Results (legacy)
Instructions to use yuriyvnv/Qwen3-ASR-1.7B-EN-Medical with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yuriyvnv/Qwen3-ASR-1.7B-EN-Medical with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="yuriyvnv/Qwen3-ASR-1.7B-EN-Medical")# Load model directly from transformers import Qwen3ASRForTraining model = Qwen3ASRForTraining.from_pretrained("yuriyvnv/Qwen3-ASR-1.7B-EN-Medical", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add test_results.json
Browse files- test_results.json +10 -0
test_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"wer": 24.56,
|
| 4 |
+
"cer": 15.07,
|
| 5 |
+
"num_samples": 7545,
|
| 6 |
+
"model": "qwen3-asr-1.7b-multimed_en-en-seed42",
|
| 7 |
+
"language": "en",
|
| 8 |
+
"test_set": "multimed_en_test"
|
| 9 |
+
}
|
| 10 |
+
]
|