Instructions to use Nuwaisir/Quran_speech_recognizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Nuwaisir/Quran_speech_recognizer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Nuwaisir/Quran_speech_recognizer")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Nuwaisir/Quran_speech_recognizer") model = AutoModelForCTC.from_pretrained("Nuwaisir/Quran_speech_recognizer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 370 Bytes
7381636 | 1 | {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "/", "return_attention_mask": false, "do_normalize": true, "special_tokens_map_file": "special_tokens_map.json", "name_or_path": "elgeish/wav2vec2-large-xlsr-53-arabic", "tokenizer_file": null, "tokenizer_class": "Wav2Vec2CTCTokenizer"} |