Automatic Speech Recognition
Transformers
Safetensors
Khmer
English
wav2vec2
speech
khmer
code-switching
mms
ctc
Eval Results (legacy)
Instructions to use nphearum/PsarAI-ASR-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nphearum/PsarAI-ASR-1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nphearum/PsarAI-ASR-1B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("nphearum/PsarAI-ASR-1B") model = AutoModelForCTC.from_pretrained("nphearum/PsarAI-ASR-1B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from nphearum/PsarAI-ASR-1B: direct link, hf CLI and curl.
- Browser
- Download file 297 Bytes
-
https://huggingface.co/nphearum/PsarAI-ASR-1B/resolve/main/processor_config.json
- Command line
-
hf download hf://nphearum/PsarAI-ASR-1B/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/nphearum/PsarAI-ASR-1B/resolve/main/processor_config.json
297 Bytes
| { | |
| "feature_extractor": { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| }, | |
| "processor_class": "Wav2Vec2Processor" | |
| } | |