You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

SeamlessM4T-v2 Bahnar-Vietnamese S2TT

This model is a fine-tuned version of facebook/seamless-m4t-v2-large for Speech-to-Text Translation from Bahnar to Vietnamese.

Note: This model only supports the Speech-to-Text Translation (S2TT) task.

Dataset

This model was trained on the Bahnar Speech Translation Dataset. The dataset was curated from internet sources and processed using automatic alignment techniques. For more details on the data creation process, refer to the dataset's README or the repository linked below.

Evaluation

Results on the test set:

BLEU Score: 24.58
Signature: nrefs:1|case:lc|eff:no|tok:13a|smooth:exp|version:2.6.

Citation

If you use this model or the dataset, please cite the following repository: https://github.com/damcuong8/Bahnar-Vietnamese-S2TT

Downloads last month: 30

Safetensors

Model size

2B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for cuong06/seamlessm4t-v2-Bahnar-Vietnamese

Base model

facebook/seamless-m4t-v2-large

Finetuned

(17)

this model

Evaluation results

BLEU (nrefs:1|case:lc|eff:no|tok:13a|smooth:exp|version:2.6.) on Bahnar Speech Translation Dataset
self-reported

24.580