IndicWav2Vec-印地语

这是一个基于Wav2Vec2架构的自动语音识别模型，使用fairseq框架训练，并迁移至Hugging Face平台。有关数据集详情、训练配置及HuggingFace格式转换的完整说明，请参阅IndicWav2Vec代码库。
注：本模型不支持结合语言模型进行推理。

推理运行脚本

import torch
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torchaudio.functional as F

DEVICE_ID = "cuda" if torch.cuda.is_available() else "cpu"
MODEL_ID = "ai4bharat/indicwav2vec-hindi"

sample = next(iter(load_dataset("common_voice", "hi", split="test", streaming=True)))
resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48000, 16000).numpy()

model = AutoModelForCTC.from_pretrained(MODEL_ID).to(DEVICE_ID)
processor = AutoProcessor.from_pretrained(MODEL_ID)

input_values = processor(resampled_audio, return_tensors="pt").input_values

with torch.no_grad():
    logits = model(input_values.to(DEVICE_ID)).logits.cpu()
    
prediction_ids = torch.argmax(logits, dim=-1)
output_str = processor.batch_decode(prediction_ids)[0]
print(f"贪心解码结果: {output_str}")

关于AI4Bharat

• 官网: https://ai4bharat.org/
• 代码库: https://github.com/AI4Bharat
• HuggingFace主页: https://huggingface.co/ai4bharat