Instructions to use dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript") model = AutoModelForSpeechSeq2Seq.from_pretrained("dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript", device_map="auto") - Notebooks
- Google Colab
- Kaggle
whisper-large-v3-chichewa-variant-b-normalized-transcript / mms-1b-all-chichewa-1h /checkpoint-2000 /preprocessor_config.json
Download mms-1b-all-chichewa-1h/checkpoint-2000/preprocessor_config.json from dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript: direct link, hf CLI and curl.
- Browser
- Download file 214 Bytes
-
https://huggingface.co/dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript/resolve/main/mms-1b-all-chichewa-1h/checkpoint-2000/preprocessor_config.json
- Command line
-
hf download hf://dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript/mms-1b-all-chichewa-1h/checkpoint-2000/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/dmatekenya/whisper-large-v3-chichewa-variant-b-normalized-transcript/resolve/main/mms-1b-all-chichewa-1h/checkpoint-2000/preprocessor_config.json
214 Bytes
| { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |