Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Persian
whisper
Generated from Trainer
Eval Results (legacy)
Instructions to use SadeghK/whisper-large-v3-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SadeghK/whisper-large-v3-turbo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="SadeghK/whisper-large-v3-turbo")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("SadeghK/whisper-large-v3-turbo") model = AutoModelForSpeechSeq2Seq.from_pretrained("SadeghK/whisper-large-v3-turbo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from SadeghK/whisper-large-v3-turbo: direct link, hf CLI and curl.
- Browser
- Download file 340 Bytes
-
https://huggingface.co/SadeghK/whisper-large-v3-turbo/resolve/be5787fb05df7eadeb90af79612b77c876af01e9/preprocessor_config.json
- Command line
-
hf download hf://SadeghK/whisper-large-v3-turbo@be5787fb05df7eadeb90af79612b77c876af01e9/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/SadeghK/whisper-large-v3-turbo/resolve/be5787fb05df7eadeb90af79612b77c876af01e9/preprocessor_config.json
340 Bytes
| { | |
| "chunk_length": 30, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "WhisperProcessor", | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |