Wav2vec2 Large Xls R 1b Swedish

🚀 wav2vec2-large-xls-r-1b-Swedish

This model is a fine - tuned version of facebook/wav2vec2-xls-r-1b on the common_voice dataset. It's designed for automatic speech recognition, achieving excellent results on Swedish speech recognition tasks.

📚 Documentation

Model Information

Evaluation Results

This model achieves the following results on the evaluation set:

Without LM

• Loss: 0.3370
• Wer: 18.44
• Cer: 5.75

With LM

• Loss: 0.3370
• Wer: 14.04
• Cer: 4.86

Evaluation Commands

1. To evaluate on mozilla - foundation/common_voice_8_0 with split test

python eval.py --model_id kingabzpro/wav2vec2-large-xls-r-1b-Swedish --dataset mozilla-foundation/common_voice_8_0 --config sv-SE --split test

2. To evaluate on speech - recognition - community - v2/dev_data

python eval.py --model_id kingabzpro/wav2vec2-large-xls-r-1b-Swedish --dataset speech-recognition-community-v2/dev_data --config sv --split validation --chunk_length_s 5.0 --stride_length_s 1.0

Inference With LM

import torch
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torchaudio.functional as F
model_id = "kingabzpro/wav2vec2-large-xls-r-1b-Swedish"
sample_iter = iter(load_dataset("mozilla-foundation/common_voice_8_0", "sv-SE", 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

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 7.5e - 05
• train_batch_size: 64
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.17.0.dev0
• Pytorch 1.10.2+cu102
• Datasets 1.18.2.dev0
• Tokenizers 0.11.0

Model Index

• Name: wav2vec2-large-xls-r-1b-Swedish Results:
  • Task: Type: automatic - speech - recognition Name: Speech Recognition Dataset: Name: Common Voice sv - SE Type: mozilla - foundation/common_voice_8_0 Args: sv - SE Metrics:
    • Type: wer Value: 14.04 Name: Test WER With LM
    • Type: cer Value: 4.86 Name: Test CER With LM
  • Task: Type: automatic - speech - recognition Name: Automatic Speech Recognition Dataset: Name: Robust Speech Event - Dev Data Type: speech - recognition - community - v2/dev_data Args: sv Metrics:
    • Type: wer Value: 29.69 Name: Test WER
    • Type: cer Value: 12.59 Name: Test CER