wav2vec2-base-timit-finetune

rohitp1/wav2vec2-base-timit-finetune

wav2vec2-base-timit-finetune is a automatic speech recognition model from rohitp1. 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

3% of all-time downloads

All-time downloads

255

Public

Repo size

14 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin378 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: Dec 25, 2022
Updated: Jan 2, 2023
SHA: 8a0bc973

Model card

From the Hugging Face model README

wav2vec2-base-timit-finetune

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:

Loss: 972.3115
Wer: 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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1000
num_epochs: 60
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3325.1297	1.39	100	4054.7283	1.0
1624.4673	2.77	200	1100.8928	1.0
1079.3557	4.17	300	1009.5025	1.0
1026.4995	5.55	400	979.0	1.0
1005.6487	6.94	500	964.3292	1.0
1000.4138	8.33	600	972.3115	1.0

Framework versions

Transformers 4.24.0
Pytorch 1.12.1
Datasets 2.7.0
Tokenizers 0.11.0

Task: Automatic Speech Recognition
Library: transformers
Type: wav2vec2
License: apache-2.0
Created: Dec 25, 2022
Updated: Jan 2, 2023