Hugging Face's logo

Ducnt17
/
finetune_nguyenvulebinh_wav2vec2_250h_vivos_dataset

Automatic Speech Recognition
Safetensors
Vietnamese
English
wav2vec2
Model card Files
xet
Community

Fine-tuned Wav2Vec2 for Vietnamese

This model is fine-tuned from nguyenvulebinh/wav2vec2-base-vietnamese-250h for ASR.

Usage 

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
model = Wav2Vec2ForCTC.from_pretrained("Ducnt17/finetune_nguyenvulebinh_wav2vec2_250h_vivos_dataset")
processor = Wav2Vec2Processor.from_pretrained("Ducnt17/finetune_nguyenvulebinh_wav2vec2_250h_vivos_dataset")
Downloads last month
-
Safetensors
Model size
94.5M params
Tensor type
F32
·
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Ducnt17/finetune_nguyenvulebinh_wav2vec2_250h_vivos_dataset

Base model

nguyenvulebinh/wav2vec2-base-vietnamese-250h
Finetuned
(63)
this model

Dataset used to train Ducnt17/finetune_nguyenvulebinh_wav2vec2_250h_vivos_dataset