Automatic Speech Recognition
Transformers
Safetensors
English
msp_audio
custom_code
msp
audio
ctc
speech-recognition
ASR
Instructions to use MahmoodAnaam/MSP-ASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MahmoodAnaam/MSP-ASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="MahmoodAnaam/MSP-ASR", trust_remote_code=True)# Load model directly from transformers import AutoModelForCTC model = AutoModelForCTC.from_pretrained("MahmoodAnaam/MSP-ASR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from MahmoodAnaam/MSP-ASR: direct link, hf CLI and curl.
- Browser
- Download file 556 Bytes
-
https://huggingface.co/MahmoodAnaam/MSP-ASR/resolve/main/processor_config.json
- Command line
-
hf download hf://MahmoodAnaam/MSP-ASR/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/MahmoodAnaam/MSP-ASR/resolve/main/processor_config.json
556 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_msp_audio.MSPAudioProcessor" | |
| }, | |
| "feature_extractor": { | |
| "auto_map": { | |
| "AutoFeatureExtractor": "feature_extraction_msp_audio.MSPAudioFeatureExtractor", | |
| "AutoProcessor": "processing_msp_audio.MSPAudioProcessor" | |
| }, | |
| "do_normalize": true, | |
| "feature_extractor_type": "MSPAudioFeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| }, | |
| "processor_class": "MSPAudioProcessor" | |
| } | |