Create README.md

README.md

@@ -0,0 +1,41 @@
+---
+language:
+- sv
+pipeline_tag: automatic-speech-recognition
+---
+## KB-Whisper Large (Beta)
+
+Preliminary checkpoint of the National Library of Sweden's new Whisper models for Swedish. This version is for testing only, it has completed its first stage of continued pre-training. We will be doing additional post-training to reduce hallucations before releasing the final version of the model.
+
+### Usage
+
+```python
+import torch
+from datasets import load_dataset
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+model_id = "KBLab/kb-whisper-large-beta"
+
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    model_id, torch_dtype=torch_dtype, use_safetensors=True, cache_dir="cache"
+)
+model.to(device)
+processor = AutoProcessor.from_pretrained(model_id)
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    torch_dtype=torch_dtype,
+    device=device,
+)
+
+generate_kwargs = {"task": "transcribe", "language": "sv"}
+# Add return_timestamps=True for output with timestamps
+res = pipe("audio.mp3", 
+           chunk_length_s=30,
+           generate_kwargs={"task": "transcribe", "language": "sv"})
+```