Automatic Speech Recognition
Transformers
Safetensors
English
joint_aed_ctc_speech-encoder-decoder
custom_code
Eval Results (legacy)
Instructions to use BUT-FIT/ED-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BUT-FIT/ED-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="BUT-FIT/ED-small", trust_remote_code=True)# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("BUT-FIT/ED-small", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload feature extractor
Browse files- preprocessor_config.json +12 -0
preprocessor_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_ceptral_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Speech2TextFeatureExtractor",
|
| 4 |
+
"feature_size": 80,
|
| 5 |
+
"normalize_means": true,
|
| 6 |
+
"normalize_vars": true,
|
| 7 |
+
"num_mel_bins": 80,
|
| 8 |
+
"padding_side": "right",
|
| 9 |
+
"padding_value": 0.0,
|
| 10 |
+
"return_attention_mask": true,
|
| 11 |
+
"sampling_rate": 16000
|
| 12 |
+
}
|