Merge branch 'main' of hf.co:alvanlii/wav2vec2-BERT-cantonese

README.md

@@ -41,7 +41,28 @@ bert_asr = pipeline(
 )
 text = pipe(file)["text"]
 ```
+or 
+```
+import torch
+import soundfile as sf
+from transformers import AutoModelForCTC, Wav2Vec2BertProcessor
+
+model_name = "alvanlii/wav2vec2-BERT-cantonese"
+
+asr_model = AutoModelForCTC.from_pretrained(model_name).to(device)
+processor = Wav2Vec2BertProcessor.from_pretrained(model_name)
+
+audio_input, _ = sf.read(file)
 
+inputs = processor([audio_input], sampling_rate=16_000).input_features
+features = torch.tensor(inputs)
+
+with torch.no_grad():
+  logits = asr_model(features).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+predictions = processor.batch_decode(predicted_ids)
+```
 
 ## Training Hyperparameters
 - learning_rate: 1e-4