Hugging Face's logo

aasem
/
wav2vec2-xls-r-300m-Urdu

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Inference Endpoints
Model card Files Community
Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co./docs/hub/model-cards#model-card-metadata)

datasets: 

common_voice: ~

language: 

ur: ~

library_name: transformers: ~ license: mit: ~ metrics: 

wer: ~

model-index: 

name: 
  wav2vec2-xls-r-300m-Urdu: ~
results: 
  - 
    task: 
      dataset: 
        args: 
          ur: ~
        name: 
          : "common_voice"
          : ~
        type: 
          common_voice: ~
      metrics: 
        - 
          type: 
            wer: ~
          value: 
            0.2459: ~
        - 
          type: 
            cer: ~
          value: 
            0.0691: ~
      type: 
        automatic-speech-recognition: ~

tags: 

audio: ~

- automatic-speech-recognition: ~ 

speech: ~

Finetuning of Facebook's 300M model on Common Voice 8.0 Urdu dataset

Downloads last month
6
Inference Examples
Automatic Speech Recognition
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.