Automatic Speech Recognition
Transformers
PyTorch
English
speech_to_text_transformer
text-generation
audio
Instructions to use valhalla/s2t_librispeech_medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use valhalla/s2t_librispeech_medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="valhalla/s2t_librispeech_medium")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("valhalla/s2t_librispeech_medium", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
db24822
1
Parent(s): 66794f1
Update config.json
Browse files- config.json +1 -0
config.json
CHANGED
|
@@ -31,6 +31,7 @@
|
|
| 31 |
"input_channels": 1,
|
| 32 |
"input_feat_per_channel": 80,
|
| 33 |
"is_encoder_decoder": true,
|
|
|
|
| 34 |
"max_position_embeddings": 1024,
|
| 35 |
"max_source_positions": 6000,
|
| 36 |
"max_target_positions": 1024,
|
|
|
|
| 31 |
"input_channels": 1,
|
| 32 |
"input_feat_per_channel": 80,
|
| 33 |
"is_encoder_decoder": true,
|
| 34 |
+
"max_length": 200,
|
| 35 |
"max_position_embeddings": 1024,
|
| 36 |
"max_source_positions": 6000,
|
| 37 |
"max_target_positions": 1024,
|