Instructions to use nyralabs/CrisperWhisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyralabs/CrisperWhisper with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nyralabs/CrisperWhisper")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nyralabs/CrisperWhisper") model = AutoModelForSpeechSeq2Seq.from_pretrained("nyralabs/CrisperWhisper", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -97,6 +97,11 @@ The following table uses the metrics as defined in the paper. For this table we
|
|
| 97 |
|
| 98 |
Here's how to use CrisperWhisper in your Python scripts:
|
| 99 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
### 2.1 Usage with 🤗 transformers
|
| 101 |
|
| 102 |
|
|
|
|
| 97 |
|
| 98 |
Here's how to use CrisperWhisper in your Python scripts:
|
| 99 |
|
| 100 |
+
First install our custom transformers fork for the most accurate timestamps:
|
| 101 |
+
```
|
| 102 |
+
pip install git+https://github.com/nyrahealth/transformers.git@crisper_whisper
|
| 103 |
+
```
|
| 104 |
+
|
| 105 |
### 2.1 Usage with 🤗 transformers
|
| 106 |
|
| 107 |
|