Hugging Face's logo

codewithdark
/
WhisperLiveSubs

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Urdu
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
codewithdark commited on
Commit
046c1ca
·
verified ·
1 Parent(s): de2c3fb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -35,7 +35,7 @@ model = WhisperForConditionalGeneration.from_pretrained("codewithdark/WhisperLiv
35
  ```
36
 
37
  ### Training Data
38
- The model was fine-tuned on the Mozilla Common Voice dataset, specifically the Urdu subset. The dataset consists of approximately [number of hours] of transcribed Urdu speech.
39
 
40
  #### Preprocessing
41
  The audio was resampled to 16kHz, and text was tokenized using the Whisper tokenizer configured for Urdu.
 
35
  ```
36
 
37
  ### Training Data
38
+ The model was fine-tuned on the Mozilla Common Voice dataset, specifically the Urdu subset. The dataset consists of approximately 141 hr of transcribed Urdu speech.
39
 
40
  #### Preprocessing
41
  The audio was resampled to 16kHz, and text was tokenized using the Whisper tokenizer configured for Urdu.