Thomas Chaigneau chainyo

## tokenizer_training.py
from datasets import load_dataset
from transformers import AutoTokenizer


dataset = load_dataset("oscar-corpus/OSCAR-2201", "fr", split="train", streaming=True)

tokenizer = AutoTokenizer.from_pretrained("pegasus-large")

length = 1_000_000
iter_dataset = iter(dataset)

## wordcab_get_stats.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_change_speaker_labels.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_delete_job.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_list_jobs.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_list_summaries.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_list_transcripts.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_retrieve_job.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_retrieve_summary.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login

## wordcab_retrieve_transcript.py
"""🚀 Wordcab Python Package Gist

To install the Wordcab package:

$ pip install wordcab

To login to Wordcab API with your API key:

$ wordcab login
	from datasets import load_dataset
	from transformers import AutoTokenizer


	dataset = load_dataset("oscar-corpus/OSCAR-2201", "fr", split="train", streaming=True)

	tokenizer = AutoTokenizer.from_pretrained("pegasus-large")

	length = 1_000_000
	iter_dataset = iter(dataset)
	"""🚀 Wordcab Python Package Gist

	To install the Wordcab package:

	$ pip install wordcab

	To login to Wordcab API with your API key:

	$ wordcab login