wav2vec2-large-xlsr-53-punjabi

should probably proofread and complete it, then remove this comment. --> This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-punjabi-pam-10](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-punjabi-pam-10) on the common_voice dataset. It achieves the following results on the evaluation set: - Loss: 1.2101 - Wer: 0.4939 - Cer: 0.2238 1. To evaluate on `mozilla-foundation/common_voice_8_0` with split `test` python eval.py --model_id kingabzpro/wav2vec2-large-xlsr-53-punjabi --dataset mozilla-foundation/common_voice_8_0 --config pa-IN --split test import torch from datasets import load_dataset from transformers import AutoModelForCTC, AutoProcessor import torchaudio.functional as F model_id = "kingabzpro/wav2vec2-large-xlsr-53-punjabi" sample_iter = iter(load_dataset("mozilla-foundation/common_voice_8_0", "pa-IN", split="test", streaming=True, use_auth_token=True)) sample = next(sample_iter) resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy() model = AutoModelForCTC.from_pretrained(model_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).logits transcription = processor.batch_decode(logits.numpy()).text The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 200 - num_epochs: 30 - mixed_precision_training: Native AMP - Transformers 4.17.0.dev0 - Pytorch 1.10.2+cu102 - Datasets 1.18.2.dev0 - Tokenizers 0.11.0