Transformers
PyTorch
multilingual
seamless_basic
audio
text
multimodal
seamless
subtitle-editing-time-prediction
Instructions to use videoloc/seamless-basic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use videoloc/seamless-basic with Transformers:
# Load model directly from transformers import HFSeamlessBasic model = HFSeamlessBasic.from_pretrained("videoloc/seamless-basic", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -79,7 +79,6 @@ spec.loader.exec_module(collator_module)
|
|
| 79 |
processor="facebook/hf-seamless-m4t-medium",
|
| 80 |
max_audio_length_sec=8.0,
|
| 81 |
max_text_length=256
|
| 82 |
-
# normalization_type="none" is default
|
| 83 |
)
|
| 84 |
|
| 85 |
# Prepare your data
|
|
|
|
| 79 |
processor="facebook/hf-seamless-m4t-medium",
|
| 80 |
max_audio_length_sec=8.0,
|
| 81 |
max_text_length=256
|
|
|
|
| 82 |
)
|
| 83 |
|
| 84 |
# Prepare your data
|