Update README.md

README.md

@@ -14,6 +14,39 @@ pipeline_tag: automatic-speech-recognition
 🤗 <a href="https://huggingface.co/Oblivion208" target="_blank">HF Repo</a>  •🐱 <a href="https://github.com/fengredrum/finetune-whisper-lora" target="_blank">Github Repo</a> 
 </p>
 
+## Usage
+```python
+import torch
+import librosa
+from transformers import WhisperProcessor, WhisperTokenizer, WhisperForConditionalGeneration
+
+# Setups
+model_name_or_path = "Oblivion208/whisper-tiny-cantonese"
+task = "transcribe"
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+
+model = WhisperForConditionalGeneration.from_pretrained(model_name_or_path).to(device)
+tokenizer = WhisperTokenizer.from_pretrained(model_name_or_path, task=task)
+processor = WhisperProcessor.from_pretrained(model_name_or_path, task=task)
+feature_extractor = processor.feature_extractor
+model.config.forced_decoder_ids = None
+model.config.suppress_tokens = []
+
+filepath = 'test.wav'
+audio, sr = librosa.load(filepath, sr=16000, mono=True)
+inputs = processor(audio, sample_rate=sr, return_tensors="pt").to(device)
+
+with torch.inference_mode():
+    generated_tokens = model.generate(
+        input_features=inputs.input_features,
+        return_dict_in_generate=True,
+        max_new_tokens=255,
+    )
+    transcription = tokenizer.batch_decode(
+        generated_tokens.sequences, skip_special_tokens=True)
+    print(transcription)
+```
+
 ## Approximate Performance Evaluation
 
 The following models are all trained and evaluated on a single RTX 3090 GPU.