---
datasets:
- mozilla-foundation/common_voice_13_0
language:
- zh
base_model:
- openai/whisper-large-v3-turbo
pipeline_tag: automatic-speech-recognition
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This model card describes a fine-tuned version of the [Openai/Whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo), optimized for Mandarin automatic speech recognition (ASR). It achieves the following results on the evaluation set:
<br>
- Common Voice 13.0 dataset(test):<br>
Wer before fine-tune: 77.08
<br>
Wer after fine-tune: 45.47
<br>
- Common Voice 16.1 dataset(test):<br>
Wer before fine-tune: 77.57
<br>
Wer after fine-tune: 45.9


## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
```bash
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 = "sandy1990418/whisper-large-v3-turbo-zh-tw"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
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,
)

dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]

result = pipe(sample)
print(result["text"])

```