Transformers
Safetensors
whisper
ASR
Automatic Speech Recognition
Whisper
Medusa
Speech
Speculative Decoding
Instructions to use aiola/whisper-medusa-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aiola/whisper-medusa-v1 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("aiola/whisper-medusa-v1") model = AutoModel.from_pretrained("aiola/whisper-medusa-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,8 @@ The Medusa heads were optimized for English, so for optimal performance and spee
|
|
| 30 |
---------
|
| 31 |
|
| 32 |
## Usage
|
|
|
|
|
|
|
| 33 |
Inference can be done using the following code:
|
| 34 |
```python
|
| 35 |
import torch
|
|
|
|
| 30 |
---------
|
| 31 |
|
| 32 |
## Usage
|
| 33 |
+
To use `whisper-medusa-v1` install [`whisper-medusa`](https://github.com/aiola-lab/whisper-medusa) repo following the README instructions.
|
| 34 |
+
|
| 35 |
Inference can be done using the following code:
|
| 36 |
```python
|
| 37 |
import torch
|