Automatic Speech Recognition
Transformers
Safetensors
Khmer
qwen3_asr
speech
audio
khmer
qwen3-asr
Eval Results (legacy)
Instructions to use seanghay/Qwen3-ASR-0.6B-Khmer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seanghay/Qwen3-ASR-0.6B-Khmer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="seanghay/Qwen3-ASR-0.6B-Khmer")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("seanghay/Qwen3-ASR-0.6B-Khmer") model = AutoModelForMultimodalLM.from_pretrained("seanghay/Qwen3-ASR-0.6B-Khmer") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -86,7 +86,6 @@ model = Qwen3ASRModel.from_pretrained(
|
|
| 86 |
|
| 87 |
results = model.transcribe(
|
| 88 |
audio="path/to/khmer.wav", # local path, URL, base64, or (np.ndarray, sr)
|
| 89 |
-
language="Khmer", # force Khmer decoding
|
| 90 |
)
|
| 91 |
|
| 92 |
print(results[0].text)
|
|
|
|
| 86 |
|
| 87 |
results = model.transcribe(
|
| 88 |
audio="path/to/khmer.wav", # local path, URL, base64, or (np.ndarray, sr)
|
|
|
|
| 89 |
)
|
| 90 |
|
| 91 |
print(results[0].text)
|