facebook_wav2vec2-xls-r-300m_command_5_second_10h

namkyeong/facebook_wav2vec2-xls-r-300m_command_5_second_10h

facebook_wav2vec2-xls-r-300m_command_5_second_10h is a automatic speech recognition model from namkyeong. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

1% of all-time downloads

All-time downloads

425

Public

Repo size

239 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.3 GB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: Jul 4, 2024
Updated: Jul 10, 2024
SHA: 210b377d

Model card

From the Hugging Face model README

facebook_wav2vec2-xls-r-300m_command_5_second_10h

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

Loss: 30.1702
Cer: 1.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 64
eval_batch_size: 64
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: 500
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
57.0768	0.71	30	77.6296	1.0
40.2674	1.42	60	47.2930	1.0
29.1638	2.14	90	38.6357	1.0
23.2974	2.85	120	30.1702	1.0

Framework versions

Transformers 4.17.0
Pytorch 1.10.0+cu113
Datasets 2.20.0
Tokenizers 0.15.2

Task: Automatic Speech Recognition
Library: transformers
Type: wav2vec2
License: apache-2.0
Created: Jul 4, 2024
Updated: Jul 10, 2024