Automatic Speech Recognition
Transformers
ONNX
Safetensors
Japanese
moonshine_streaming
speech
japanese
streaming
low-latency
on-device
Instructions to use ayousanz/kodama-ja-streaming-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ayousanz/kodama-ja-streaming-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ayousanz/kodama-ja-streaming-small")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ayousanz/kodama-ja-streaming-small") model = AutoModelForSpeechSeq2Seq.from_pretrained("ayousanz/kodama-ja-streaming-small", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "processor_class": "MoonshineStreamingProcessor", | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "tokenizer_class": "PreTrainedTokenizerFast" | |
| } | |