umt5-base-asr

urarik/umt5-base-asr

umt5-base-asr is a machine learning model from urarik. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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

26% of all-time downloads

All-time downloads

Public

Parameters

592M

49.8 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.3 GB · 98%

Parameter types

How the weights are stored.

F16554M · 94%

Base models

google/umt5-base

Model card

From the Hugging Face model README

umt5-base-asr

This model is a fine-tuned version of google/umt5-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 61.5938
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: 5e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 1024
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
9.5449	0.9994	99	73.375	1.0
9.1592	1.9893	198	37.5625	1.0023
9.0479	2.9792	297	63.2812	1.0
8.3572	3.9691	396	41.375	1.0
8.6292	4.9590	495	61.5938	1.0

Framework versions

Transformers 4.51.3
Pytorch 2.5.1+cu124
Datasets 2.17.1
Tokenizers 0.21.0

Library: transformers
Type: umt5
License: apache-2.0
Created: May 9, 2025
Updated: May 15, 2025