Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Spanish
whisper
Noe tags
Generated from Trainer
Instructions to use kirah/fcv_s2t with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kirah/fcv_s2t with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="kirah/fcv_s2t")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("kirah/fcv_s2t") model = AutoModelForSpeechSeq2Seq.from_pretrained("kirah/fcv_s2t") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -26,7 +26,7 @@
|
|
| 26 |
"forced_decoder_ids": null,
|
| 27 |
"init_std": 0.02,
|
| 28 |
"is_encoder_decoder": true,
|
| 29 |
-
"max_length":
|
| 30 |
"max_source_positions": 1500,
|
| 31 |
"max_target_positions": 448,
|
| 32 |
"model_type": "whisper",
|
|
|
|
| 26 |
"forced_decoder_ids": null,
|
| 27 |
"init_std": 0.02,
|
| 28 |
"is_encoder_decoder": true,
|
| 29 |
+
"max_length": 2000,
|
| 30 |
"max_source_positions": 1500,
|
| 31 |
"max_target_positions": 448,
|
| 32 |
"model_type": "whisper",
|