Instructions to use Ryenhails/w2v-bert-2.0-geo-all-train_withSpec with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ryenhails/w2v-bert-2.0-geo-all-train_withSpec with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Ryenhails/w2v-bert-2.0-geo-all-train_withSpec")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Ryenhails/w2v-bert-2.0-geo-all-train_withSpec") model = AutoModelForCTC.from_pretrained("Ryenhails/w2v-bert-2.0-geo-all-train_withSpec", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Ryenhails/w2v-bert-2.0-geo-all-train_withSpec: direct link, hf CLI and curl.
- Browser
- Download file 275 Bytes
-
https://huggingface.co/Ryenhails/w2v-bert-2.0-geo-all-train_withSpec/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Ryenhails/w2v-bert-2.0-geo-all-train_withSpec/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Ryenhails/w2v-bert-2.0-geo-all-train_withSpec/resolve/main/preprocessor_config.json
275 Bytes
| { | |
| "feature_extractor_type": "SeamlessM4TFeatureExtractor", | |
| "feature_size": 80, | |
| "num_mel_bins": 80, | |
| "padding_side": "right", | |
| "padding_value": 1, | |
| "processor_class": "Wav2Vec2BertProcessor", | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "stride": 2 | |
| } | |