File size: 1,245 Bytes
9d4f6e6 40af4cd 4618356 40af4cd 9d4f6e6 40af4cd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 |
---
language:
- sv
pipeline_tag: automatic-speech-recognition
---
## KB-Whisper Small (Beta)
Preliminary checkpoint of the National Library of Sweden's new Whisper models for Swedish. This version is for testing only, it has only trained 40% of the total training time.
### 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-small-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"})
``` |