Instructions to use Shaelois/MeetingScript with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shaelois/MeetingScript with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="Shaelois/MeetingScript")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Shaelois/MeetingScript") model = AutoModelForSeq2SeqLM.from_pretrained("Shaelois/MeetingScript", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,7 @@ metrics:
|
|
| 9 |
base_model:
|
| 10 |
- google/bigbird-pegasus-large-bigpatent
|
| 11 |
pipeline_tag: summarization
|
|
|
|
| 12 |
---
|
| 13 |
# MeetingScript
|
| 14 |
|
|
@@ -47,5 +48,4 @@ Evaluated on the held‑out test split of MeetingBank (≈ 600 transcripts), us
|
|
| 47 |
## Training Data
|
| 48 |
Dataset: MeetingBank
|
| 49 |
Splits: Train (5000+), Validation (600+), Test (600+)
|
| 50 |
-
Preprocessing: Sliding‑window chunking for sequences > 4096 tokens
|
| 51 |
-
|
|
|
|
| 9 |
base_model:
|
| 10 |
- google/bigbird-pegasus-large-bigpatent
|
| 11 |
pipeline_tag: summarization
|
| 12 |
+
library_name: transformers
|
| 13 |
---
|
| 14 |
# MeetingScript
|
| 15 |
|
|
|
|
| 48 |
## Training Data
|
| 49 |
Dataset: MeetingBank
|
| 50 |
Splits: Train (5000+), Validation (600+), Test (600+)
|
| 51 |
+
Preprocessing: Sliding‑window chunking for sequences > 4096 tokens
|
|
|