Instructions to use bezzam/parakeet-ctc-1.1b-hf-sequential with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bezzam/parakeet-ctc-1.1b-hf-sequential with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bezzam/parakeet-ctc-1.1b-hf-sequential")# Load model directly from transformers import AutoModelForCTC model = AutoModelForCTC.from_pretrained("bezzam/parakeet-ctc-1.1b-hf-sequential", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload feature extractor
Browse files- preprocessor_config.json +1 -0
preprocessor_config.json
CHANGED
|
@@ -12,6 +12,7 @@
|
|
| 12 |
"padding_side": "right",
|
| 13 |
"padding_value": 0.0,
|
| 14 |
"preemphasis": 0.97,
|
|
|
|
| 15 |
"return_attention_mask": true,
|
| 16 |
"sampling_rate": 16000,
|
| 17 |
"win_length": 400,
|
|
|
|
| 12 |
"padding_side": "right",
|
| 13 |
"padding_value": 0.0,
|
| 14 |
"preemphasis": 0.97,
|
| 15 |
+
"processor_class": "ParakeetProcessor",
|
| 16 |
"return_attention_mask": true,
|
| 17 |
"sampling_rate": 16000,
|
| 18 |
"win_length": 400,
|