Instructions to use Cathle/stt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cathle/stt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Cathle/stt")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Cathle/stt") model = AutoModelForSpeechSeq2Seq.from_pretrained("Cathle/stt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload generation_config.json with huggingface_hub
Browse files- generation_config.json +1 -0
generation_config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"decoder_start_token_id": 50258,
|
| 5 |
"eos_token_id": 50257,
|
| 6 |
"max_length": 225,
|
|
|
|
| 7 |
"pad_token_id": 50257,
|
| 8 |
"suppress_tokens": [],
|
| 9 |
"transformers_version": "4.52.2"
|
|
|
|
| 4 |
"decoder_start_token_id": 50258,
|
| 5 |
"eos_token_id": 50257,
|
| 6 |
"max_length": 225,
|
| 7 |
+
"no_timestamps_token_id": 50363,
|
| 8 |
"pad_token_id": 50257,
|
| 9 |
"suppress_tokens": [],
|
| 10 |
"transformers_version": "4.52.2"
|