Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Urdu
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use codewithdark/WhisperLiveSubs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use codewithdark/WhisperLiveSubs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="codewithdark/WhisperLiveSubs")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("codewithdark/WhisperLiveSubs") model = AutoModelForSpeechSeq2Seq.from_pretrained("codewithdark/WhisperLiveSubs") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -65,7 +65,7 @@ improvements can be made to enhance the model's accuracy and reduce the WER.*
|
|
| 65 |
- **Compute Region:** PK
|
| 66 |
|
| 67 |
### Model Architecture and Objective
|
| 68 |
-
The
|
| 69 |
|
| 70 |
#### Software
|
| 71 |
- **Framework:** PyTorch
|
|
|
|
| 65 |
- **Compute Region:** PK
|
| 66 |
|
| 67 |
### Model Architecture and Objective
|
| 68 |
+
The WhisperLiveSubs model is based on the Whisper architecture, designed for automatic speech recognition.
|
| 69 |
|
| 70 |
#### Software
|
| 71 |
- **Framework:** PyTorch
|