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, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4747d621061ff864406560d79c8c3e355c05f2e88ba30eba88c8d5881d3d220d
- Size of remote file:
- 4.24 MB
- SHA256:
- 61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.