Automatic Speech Recognition
Transformers
PyTorch
Arabic
wav2vec2
Arabic
MSA
Speech
Syllables
Wav2vec
ASR
Instructions to use IbrahimSalah/Arabic_speech_Syllables_recognition_Using_Wav2vec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IbrahimSalah/Arabic_speech_Syllables_recognition_Using_Wav2vec2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="IbrahimSalah/Arabic_speech_Syllables_recognition_Using_Wav2vec2")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("IbrahimSalah/Arabic_speech_Syllables_recognition_Using_Wav2vec2") model = AutoModelForCTC.from_pretrained("IbrahimSalah/Arabic_speech_Syllables_recognition_Using_Wav2vec2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "bos_token": null, | |
| "clean_up_tokenization_spaces": true, | |
| "do_lower_case": false, | |
| "eos_token": null, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "processor_class": "Wav2Vec2ProcessorWithLM", | |
| "replace_word_delimiter_char": " ", | |
| "target_lang": null, | |
| "tokenizer_class": "Wav2Vec2CTCTokenizer", | |
| "unk_token": "[UNK]", | |
| "word_delimiter_token": "|" | |
| } | |