Hugging Face's logo

sha1779
/
BengaliRegionalASR

Automatic Speech Recognition
PyTorch
Safetensors
Bengali
whisper
Model card Files Community
1
sha1779 commited on
Commit
3a70428
·
verified ·
1 Parent(s): 5639f1e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -25,7 +25,8 @@ processor = WhisperProcessor.from_pretrained(model_path_)
25
  model = WhisperForConditionalGeneration.from_pretrained(model_path_).to(device)
26
  model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="bengali", task="transcribe")
27
 
28
- mp3_path = "https://huggingface.co/sha1779/BengaliRegionalASR/resolve/main/Mp3/common_voice_bn_31617644.mp3"
 
29
  speech_array, sampling_rate = librosa.load(mp3_path, sr=16000)
30
 
31
  speech_array = librosa.resample(np.asarray(speech_array), orig_sr=sampling_rate, target_sr=16000)
 
25
  model = WhisperForConditionalGeneration.from_pretrained(model_path_).to(device)
26
  model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="bengali", task="transcribe")
27
 
28
+ mp3_path = "https://huggingface.co/sha1779/BengaliRegionalASR/resolve/main/Mp3/valid_barishal%20(1).wav"
29
+
30
  speech_array, sampling_rate = librosa.load(mp3_path, sr=16000)
31
 
32
  speech_array = librosa.resample(np.asarray(speech_array), orig_sr=sampling_rate, target_sr=16000)