Instructions to use alphaedge-ai/whisper-medium-rus-32768 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alphaedge-ai/whisper-medium-rus-32768 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="alphaedge-ai/whisper-medium-rus-32768")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("alphaedge-ai/whisper-medium-rus-32768") model = AutoModelForSpeechSeq2Seq.from_pretrained("alphaedge-ai/whisper-medium-rus-32768", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update model card for Russian
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ This trimmed model should perform similarly to the original model with only 32,7
|
|
| 19 |
| Metric | Original | Trimmed | Reduction |
|
| 20 |
|--------|----------|---------|-----------|
|
| 21 |
| **Vocabulary size** | 51,865 tokens | 32,768 tokens | **36.82%** |
|
| 22 |
-
| **Model size** |
|
| 23 |
|
| 24 |

|
| 25 |
|
|
|
|
| 19 |
| Metric | Original | Trimmed | Reduction |
|
| 20 |
|--------|----------|---------|-----------|
|
| 21 |
| **Vocabulary size** | 51,865 tokens | 32,768 tokens | **36.82%** |
|
| 22 |
+
| **Model size** | 763,857,920 params | 744,302,592 params | **2.56%** |
|
| 23 |
|
| 24 |

|
| 25 |
|