Update README.md

README.md

@@ -23,9 +23,47 @@ You can use this model for automatic dialectal transcription of Finnish dialects
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+```
+from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC, Wav2Vec2CTCTokenizer
+from datasets import Dataset, Audio
+import torch
+import pandas as pd
 
-TBA
+ds = pd.read_csv('CSV_DATA.csv')
+ds = ds.dropna(how='any', axis=0)
+
+test = Dataset.from_pandas(skn_test)
+test = test.cast_column("AUDIO_PATH_COLUMN", Audio(sampling_rate=16000))
+
+tokenizer = Wav2Vec2CTCTokenizer.from_pretrained("okuparinen/SKN_300m_simple", unk_token="[UNK]", pad_token="[PAD]", word_delimiter_token="|")
+model = Wav2Vec2ForCTC.from_pretrained("okuparinen/SKN_300m_simple").to("cuda")
+processor = Wav2Vec2Processor.from_pretrained("okuparinen/SKN_300m_simple", tokenizer=tokenizer)
+
+def prepare_dataset(batch):
+    audio = batch["AUDIO_PATH"]
+    batch["input_values"] = processor(audio["array"], sampling_rate=audio["sampling_rate"]).input_values[0]
+    batch["input_length"] = len(batch["input_values"])
+
+    return batch
+
+test_ready = test.map(prepare_dataset, remove_columns=test.column_names)
+
+length = len(test)
+predictions = []
+
+for i in range(0, length, 1):
+    input_dict = processor(test_ready[i]["input_values"], return_tensors="pt", padding=True)
+    logits = model(input_dict.input_values.to("cuda")).logits
+    
+    pred_ids = torch.argmax(logits, dim=-1)[0]
+    
+    prediction = processor.decode(pred_ids)
+    predictions.append(prediction)
+
+with open("OUTFILE.txt", "w") as f_pred:
+    for line in predictions:
+        f_pred.write(line + '\n')
+```
 
 ### Training Data