Automatic Speech Recognition
Transformers
Safetensors
English
joint_aed_ctc_speech-encoder-decoder
custom_code
Eval Results (legacy)
Instructions to use BUT-FIT/DeCRED-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BUT-FIT/DeCRED-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="BUT-FIT/DeCRED-base", trust_remote_code=True)# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("BUT-FIT/DeCRED-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload config
Browse files- generation_config.json +2 -1
generation_config.json
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 0,
|
| 3 |
"ctc_margin": 0,
|
| 4 |
-
"ctc_weight": 0.
|
| 5 |
"decoder_start_token_id": 0,
|
| 6 |
"eos_token_id": 1,
|
| 7 |
"max_length": 512,
|
|
|
|
| 8 |
"pad_token_id": 3,
|
| 9 |
"transformers_version": "4.39.3"
|
| 10 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token_id": 0,
|
| 3 |
"ctc_margin": 0,
|
| 4 |
+
"ctc_weight": 0.3,
|
| 5 |
"decoder_start_token_id": 0,
|
| 6 |
"eos_token_id": 1,
|
| 7 |
"max_length": 512,
|
| 8 |
+
"num_beams": 5,
|
| 9 |
"pad_token_id": 3,
|
| 10 |
"transformers_version": "4.39.3"
|
| 11 |
}
|