Instructions to use readerbench/whisper-ro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use readerbench/whisper-ro with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="readerbench/whisper-ro")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("readerbench/whisper-ro") model = AutoModelForSpeechSeq2Seq.from_pretrained("readerbench/whisper-ro") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,11 @@ model-index:
|
|
| 22 |
- name: WER
|
| 23 |
type: wer
|
| 24 |
value: 0.08668345828147764
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
---
|
| 26 |
|
| 27 |
# whisper-ro
|
|
@@ -55,4 +60,4 @@ The following hyperparameters were used during training:
|
|
| 55 |
- `lr_scheduler_type`: linear
|
| 56 |
- `lr_scheduler_warmup_steps`: 500
|
| 57 |
- `num_epochs`: 20.0
|
| 58 |
-
- `mixed_precision_training`: Native AMP
|
|
|
|
| 22 |
- name: WER
|
| 23 |
type: wer
|
| 24 |
value: 0.08668345828147764
|
| 25 |
+
language:
|
| 26 |
+
- ro
|
| 27 |
+
base_model:
|
| 28 |
+
- openai/whisper-small
|
| 29 |
+
pipeline_tag: automatic-speech-recognition
|
| 30 |
---
|
| 31 |
|
| 32 |
# whisper-ro
|
|
|
|
| 60 |
- `lr_scheduler_type`: linear
|
| 61 |
- `lr_scheduler_warmup_steps`: 500
|
| 62 |
- `num_epochs`: 20.0
|
| 63 |
+
- `mixed_precision_training`: Native AMP
|