Modelpublic

Plim/test_lm

sourceHugging Faceapache-2.0updated 5y agoView on Hugging Face

0likes22downloads

Model Card

Model description

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the MOZILLA-FOUNDATION/COMMONVOICE8_0 - FR dataset.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

—learning_rate: 7.5e-05
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—gradientaccumulationsteps: 8
—totaltrainbatch_size: 128
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_steps: 2000
—num_epochs: 4.0
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.9827	0.29	1000	inf	0.2937
1.0203	0.57	2000	inf	0.2711
1.0048	0.86	3000	inf	0.2620
0.9858	1.15	4000	inf	0.2522
0.9709	1.43	5000	inf	0.2365
0.9347	1.72	6000	inf	0.2332
0.9256	2.01	7000	inf	0.2261
0.8936	2.29	8000	inf	0.2203
0.877	2.58	9000	inf	0.2096
0.8393	2.87	10000	inf	0.2017
0.8156	3.15	11000	inf	0.1936
0.8015	3.44	12000	inf	0.1880
0.774	3.73	13000	inf	0.1834

It achieves the best result on the validation set on STEP 13000:

—Wer: 0.1834

Some problem occurs when calculating the validation loss.

Framework versions

—Transformers 4.17.0.dev0
—Pytorch 1.10.2+cu102
—Datasets 1.18.3.dev0
—Tokenizers 0.11.0

Evaluation Commands

1.To evaluate on mozilla-foundation/common_voice_8 with split test

bash

python eval.py --model_id Plim/xls-r-1b-cv_8-fr --dataset mozilla-foundation/common_voice_8_0 --config fr --split test

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

bash

python eval.py --model_id Plim/xls-r-1b-cv_8-fr --dataset speech-recognition-community-v2/dev_data --config fr --split validation --chunk_length_s 5.0 --stride_length_s 1.0