Instructions to use Qwen/Qwen3-ASR-1.7B-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-ASR-1.7B-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Qwen/Qwen3-ASR-1.7B-hf")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-ASR-1.7B-hf") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-ASR-1.7B-hf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -68,10 +68,10 @@ The Qwen3-ASR family includes **Qwen3-ASR-1.7B** and **Qwen3-ASR-0.6B**, which s
|
|
| 68 |
|
| 69 |
## Usage
|
| 70 |
|
| 71 |
-
Qwen3-ASR is supported natively in 🤗 Transformers
|
| 72 |
|
| 73 |
```bash
|
| 74 |
-
pip install
|
| 75 |
```
|
| 76 |
|
| 77 |
### Simple transcription
|
|
|
|
| 68 |
|
| 69 |
## Usage
|
| 70 |
|
| 71 |
+
Qwen3-ASR is supported natively in 🤗 Transformers, starting from v5.13.0.
|
| 72 |
|
| 73 |
```bash
|
| 74 |
+
pip install "transformers>=5.13.0"
|
| 75 |
```
|
| 76 |
|
| 77 |
### Simple transcription
|