Automatic Speech Recognition
Transformers
Safetensors
jais_asr
text-generation
jais
ifm
arabic
arabic-dialects
speech-to-text
code-switching
diacritization
language-identification
open-weights
custom_code
fp8
compressed-tensors
llm-compressor
Instructions to use IFM/Jais-ASR-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IFM/Jais-ASR-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="IFM/Jais-ASR-FP8", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("IFM/Jais-ASR-FP8", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from IFM/Jais-ASR-FP8: direct link, hf CLI and curl.
- Browser
- Download file 335 Bytes
-
https://huggingface.co/IFM/Jais-ASR-FP8/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://IFM/Jais-ASR-FP8/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/IFM/Jais-ASR-FP8/resolve/main/preprocessor_config.json
335 Bytes
| { | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 4800000, | |
| "nb_max_frames": 30000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "JaisASRProcessor", | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } |