Automatic Speech Recognition
Transformers
Safetensors
meralion3_asr
meralion3
meralion
audio
asr
southeast-asian
code-switching
custom_code
Instructions to use MERaLiON/MERaLiON-3-3B-ASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MERaLiON/MERaLiON-3-3B-ASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="MERaLiON/MERaLiON-3-3B-ASR", trust_remote_code=True)# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("MERaLiON/MERaLiON-3-3B-ASR", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f2f8f821cec4e1c410c7ee694e38022bddded7f71e5a99aaedacd91b1e6ff3dd
- Size of remote file:
- 566 kB
- SHA256:
- a683835a420a13467165d8b8e818bb0fce0ae2d6f5f31e1ef520ed0df49f3479
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.