Update README.md

README.md

@@ -38,32 +38,48 @@ import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 from datasets import load_dataset
 
-
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-model_id = "openai/whisper-large-v3"
+def download_adapter_model():
+  model_name = "whisper-v3-LoRA-en_students"
+  print(f"Downloading the adapter model '{model_name}' from the Hugging Face Hub.", flush=True)
+
+  # Define the path for the directory
+  local_directory = os.path.expanduser("~/.cache/huggingface/hub")
+
+  # Check if the directory exists
+  if not os.path.exists(local_directory):
+    # If it doesn't exist, create it
+      os.makedirs(local_directory)
+      print(f"Directory '{local_directory}' created.", flush=True)
+  else:
+    print(f"Directory '{local_directory}' already exists.", flush=True)
+
+  repo_id = f"Transducens/{model_name}"
+  repo_adapter_dir = f"{model_name}/checkpoint-5000/adapter_model"
+  repo_filename_config = f"{repo_adapter_dir}/adapter_config.json"
+  repo_filename_tensors = f"{repo_adapter_dir}/adapter_model.safetensors"
+
+  adapter_config = hf_hub_download(repo_id=repo_id, filename=repo_filename_config, local_dir=local_directory)
+  adapter_model_tensors = hf_hub_download(repo_id=repo_id, filename=repo_filename_tensors, local_dir=local_directory)
+
+  print(f"Dowloaded the adapter model '{model_name}' from the Hugging Face Hub.", flush=True)
 
-model = AutoModelForSpeechSeq2Seq.from_pretrained(
-    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
-)
-model.to(device)
+  return os.path.join(local_directory, repo_adapter_dir)
 
-processor = AutoProcessor.from_pretrained(model_id)
+peft_model_id = adapter_path # Use the same model ID as before.
+peft_config = PeftConfig.from_pretrained(peft_model_id)
+model = WhisperForConditionalGeneration.from_pretrained(
+peft_config.base_model_name_or_path, load_in_8bit=False)
 
-pipe = pipeline(
-    "automatic-speech-recognition",
-    model=model,
-    tokenizer=processor.tokenizer,
-    feature_extractor=processor.feature_extractor,
-    torch_dtype=torch_dtype,
-    device=device,
-)
+model = PeftModel.from_pretrained(model, peft_model_id)
+model.generation_config.language = "<|en|>"
+model.generation_config.task = "transcribe"
 
-dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
-sample = dataset[0]["audio"]
+tokenizer = WhisperTokenizer.from_pretrained("openai/whisper-large-v3", task="transcribe")
+feature_extractor = WhisperFeatureExtractor.from_pretrained("openai/whisper-large-v3")
 
-result = pipe(sample)
-print(result["text"])
+pipe = pipeline(model=model, tokenizer=tokenizer, feature_extractor=feature_extractor, task="automatic-speech-recognition", device=device)
 ```