Instructions to use washeed/audio-transcribe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use washeed/audio-transcribe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="washeed/audio-transcribe")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("washeed/audio-transcribe") model = AutoModelForSpeechSeq2Seq.from_pretrained("washeed/audio-transcribe") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -48,4 +48,10 @@ pipe = pipeline(
|
|
| 48 |
result = pipe("audio.mp3")
|
| 49 |
print(result["text"])
|
| 50 |
```
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
result = pipe("audio.mp3")
|
| 49 |
print(result["text"])
|
| 50 |
```
|
| 51 |
+
|
| 52 |
+
# if you want to transcribe instead of translating just replace the :
|
| 53 |
+
|
| 54 |
+
```result = pipe("audio.mp3")```
|
| 55 |
+
# with
|
| 56 |
+
``` result = pipe("inference.mp3", generate_kwargs={"task": "transcribe"})```
|
| 57 |
+
|