Instructions to use Korla/omniASR_W2V_1B_SSL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Korla/omniASR_W2V_1B_SSL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Korla/omniASR_W2V_1B_SSL")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Korla/omniASR_W2V_1B_SSL") model = AutoModelForCTC.from_pretrained("Korla/omniASR_W2V_1B_SSL", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- preprocessor_config.json +1 -0
- tokenizer_config.json +1 -0
preprocessor_config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0.0,
|
|
|
|
| 7 |
"return_attention_mask": false,
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|
|
|
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
"return_attention_mask": false,
|
| 9 |
"sampling_rate": 16000
|
| 10 |
}
|
tokenizer_config.json
CHANGED
|
@@ -40,6 +40,7 @@
|
|
| 40 |
"extra_special_tokens": {},
|
| 41 |
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
"pad_token": "[PAD]",
|
|
|
|
| 43 |
"replace_word_delimiter_char": " ",
|
| 44 |
"target_lang": null,
|
| 45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
|
| 40 |
"extra_special_tokens": {},
|
| 41 |
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
"pad_token": "[PAD]",
|
| 43 |
+
"processor_class": "Wav2Vec2Processor",
|
| 44 |
"replace_word_delimiter_char": " ",
|
| 45 |
"target_lang": null,
|
| 46 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|