Automatic Speech Recognition
Transformers
Safetensors
whisper
speech
audio
asr
shunyalabs
gated
multi-lingual
pingala-shunya
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use shunyalabs/pingala-v1-universal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shunyalabs/pingala-v1-universal with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="shunyalabs/pingala-v1-universal")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("shunyalabs/pingala-v1-universal") model = AutoModelForSpeechSeq2Seq.from_pretrained("shunyalabs/pingala-v1-universal", device_map="auto") - Notebooks
- Google Colab
- Kaggle
ONNX format
#1
by ljbred08 - opened
Would it be possible to add an ONNX conversion to enable Nodejs transcription using @huggingface/transformers (preferably the builtin ASR pipeline, but I think that currently only supports Whisper models)? This model looks promising for fast, accurate ASR on consumer hardware.
See https://www.npmjs.com/package/@huggingface/transformers.
Is it live??