mozilla-foundation/common_voice_13_0
Updated • 1.51k • 6
How to use nitinyadav250/whisper-small-hindi8 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="nitinyadav250/whisper-small-hindi8", device_map="auto") # Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("nitinyadav250/whisper-small-hindi8")
model = AutoModelForSpeechSeq2Seq.from_pretrained("nitinyadav250/whisper-small-hindi8", device_map="auto")model name: OPENAI Whisper
results: Significant reduction in wer metric for hindi language dataset
task type: Fine-tuning ASR model
dataset name:common_voice_13_0
metrics name: WER
value: 18.96
url: https://huggingface.co/nitinyadav250/whisper-small-hindi8