Instructions to use ethiospeech01/w2v2-bert-ethio-v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ethiospeech01/w2v2-bert-ethio-v5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ethiospeech01/w2v2-bert-ethio-v5")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("ethiospeech01/w2v2-bert-ethio-v5") model = AutoModelForCTC.from_pretrained("ethiospeech01/w2v2-bert-ethio-v5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from ethiospeech01/w2v2-bert-ethio-v5: direct link, hf CLI and curl.
- Browser
- Download file 316 Bytes
-
https://huggingface.co/ethiospeech01/w2v2-bert-ethio-v5/resolve/main/processor_config.json
- Command line
-
hf download hf://ethiospeech01/w2v2-bert-ethio-v5/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/ethiospeech01/w2v2-bert-ethio-v5/resolve/main/processor_config.json
316 Bytes
| { | |
| "feature_extractor": { | |
| "feature_extractor_type": "SeamlessM4TFeatureExtractor", | |
| "feature_size": 80, | |
| "num_mel_bins": 80, | |
| "padding_side": "right", | |
| "padding_value": 1, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "stride": 2 | |
| }, | |
| "processor_class": "Wav2Vec2Processor" | |
| } | |