Instructions to use ZeeshanGeoPk/haitian-speech-to-text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZeeshanGeoPk/haitian-speech-to-text with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ZeeshanGeoPk/haitian-speech-to-text")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ZeeshanGeoPk/haitian-speech-to-text") model = AutoModelForSpeechSeq2Seq.from_pretrained("ZeeshanGeoPk/haitian-speech-to-text", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Haitian Speech-to-Text Model
|
| 2 |
|
| 3 |
## Overview
|
|
@@ -44,13 +52,4 @@ predicted_ids = model.generate(input_features)
|
|
| 44 |
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
|
| 45 |
print(transcription)
|
| 46 |
|
| 47 |
-
```
|
| 48 |
-
|
| 49 |
-
---
|
| 50 |
-
license: apache-2.0
|
| 51 |
-
language:
|
| 52 |
-
- ht
|
| 53 |
-
metrics:
|
| 54 |
-
- wer
|
| 55 |
-
library_name: transformers
|
| 56 |
-
---
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- ht
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
library_name: transformers
|
| 8 |
+
---
|
| 9 |
# Haitian Speech-to-Text Model
|
| 10 |
|
| 11 |
## Overview
|
|
|
|
| 52 |
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
|
| 53 |
print(transcription)
|
| 54 |
|
| 55 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|