Downloads · 30 days
38
0% of all-time downloads
sandy1990418/whisper-large-v3-turbo-chinese
whisper-large-v3-turbo-chinese is a automatic speech recognition model from sandy1990418. Use it when you need speech turned into text.
This model card describes a fine-tuned version of the Whisper-large-v3-turbo model, optimized for Mandarin automatic speech recognition (ASR). The model was fine-tuned on the Common Voice 13.0 dataset using PEFT with…
Downloads · 30 days
38
0% of all-time downloads
All-time downloads
11K
Public
Parameters
809M
4.9 GB on disk
Likes
4
Public
Click a slice to open those files.
.safetensors1.6 GB · 100%
From the Hugging Face model README
This model card describes a fine-tuned version of the Whisper-large-v3-turbo model, optimized for Mandarin automatic speech recognition (ASR). The model was fine-tuned on the Common Voice 13.0 dataset using PEFT with LoRA to ensure efficient training while maintaining the performance of the original model. It achieves the following results on the evaluation set: <br>
Wer after fine-tune: 40.29 <br>
Wer after fine-tune: 40.39
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-chinese"
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"])