Instructions to use marinone94/whisper-tiny-sv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marinone94/whisper-tiny-sv with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="marinone94/whisper-tiny-sv")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("marinone94/whisper-tiny-sv") model = AutoModelForMultimodalLM.from_pretrained("marinone94/whisper-tiny-sv") - Notebooks
- Google Colab
- Kaggle
Commit ·
4f87524
1
Parent(s): 7036d6a
add save total
Browse files- test_run_nordic.sh +1 -0
test_run_nordic.sh
CHANGED
|
@@ -26,6 +26,7 @@ python $1run_speech_recognition_seq2seq_streaming.py \
|
|
| 26 |
--text_column_name="sentence,text,raw_transcription" \
|
| 27 |
--freeze_feature_encoder="False" \
|
| 28 |
--report_to="wandb" \
|
|
|
|
| 29 |
--metric_for_best_model="wer" \
|
| 30 |
--greater_is_better="False" \
|
| 31 |
--load_best_model_at_end \
|
|
|
|
| 26 |
--text_column_name="sentence,text,raw_transcription" \
|
| 27 |
--freeze_feature_encoder="False" \
|
| 28 |
--report_to="wandb" \
|
| 29 |
+
--save_total_limit="2" \
|
| 30 |
--metric_for_best_model="wer" \
|
| 31 |
--greater_is_better="False" \
|
| 32 |
--load_best_model_at_end \
|