Update README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,15 @@
|
|
| 2 |
language: "[en]"
|
| 3 |
datasets:
|
| 4 |
- Spotify Podcasts Dataset
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
metrics:
|
| 6 |
- ROUGE
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# T5 for Automatic Podcast Summarisation
|
|
@@ -23,7 +30,7 @@ were used for training, the model also learned to generate promotional material
|
|
| 23 |
some post processing may be required on the model's outputs.
|
| 24 |
|
| 25 |
#### How to use
|
| 26 |
-
A 'summarize:' tag must be
|
| 27 |
|
| 28 |
```python
|
| 29 |
from transformers import T5Tokenizer, T5ForConditionalGeneration
|
|
|
|
| 2 |
language: "[en]"
|
| 3 |
datasets:
|
| 4 |
- Spotify Podcasts Dataset
|
| 5 |
+
tags:
|
| 6 |
+
- t5
|
| 7 |
+
- summarisation
|
| 8 |
+
- pytorch
|
| 9 |
+
- lm-head
|
| 10 |
metrics:
|
| 11 |
- ROUGE
|
| 12 |
+
pipeline:
|
| 13 |
+
-summarisation
|
| 14 |
---
|
| 15 |
|
| 16 |
# T5 for Automatic Podcast Summarisation
|
|
|
|
| 30 |
some post processing may be required on the model's outputs.
|
| 31 |
|
| 32 |
#### How to use
|
| 33 |
+
A 'summarize:' tag must be pre-pended to the source text before it is passed to the T5 model.
|
| 34 |
|
| 35 |
```python
|
| 36 |
from transformers import T5Tokenizer, T5ForConditionalGeneration
|