Update README.md

README.md

@@ -11,18 +11,16 @@ language_abbr = "mr"
 task = "transcribe"
 dataset_name = "mozilla-foundation/common_voice_11_0"
 
+common_voice["train"] = load_dataset(dataset_name, language_abbr, split="train+validation", use_auth_token=True)
+common_voice["test"] = load_dataset(dataset_name, language_abbr, split="test", use_auth_token=True)
+
 feature_extractor = AutoFeatureExtractor.from_pretrained(model_name_or_path)
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, language=language, task=task)
 processor = AutoProcessor.from_pretrained(model_name_or_path, language=language, task=task)
 
 
-common_voice["train"] = load_dataset(dataset_name, language_abbr, split="train+validation", use_auth_token=True)
-common_voice["test"] = load_dataset(dataset_name, language_abbr, split="test", use_auth_token=True)
-
-
 model = AutoModelForSpeechSeq2Seq.from_pretrained(model_name_or_path, load_in_8bit=True, device_map="auto")
 config = LoraConfig(r=32, lora_alpha=64, target_modules=["q_proj", "v_proj"], lora_dropout=0.05, bias="none")
-
 model = get_peft_model(model, config)
 model.print_trainable_parameters()
 #"trainable params: 15728640 || all params: 1559033600 || trainable%: 1.0088711365810203"