Wav2VecBert 2.0 Khmer

This model is a fine-tuned version of facebook/w2v-bert-2.0 on the OpenSLR 42 dataset.

from transformers import pipeline
recognizer = pipeline("automatic-speech-recognition", model="seanghay/w2v-bert-2.0-khmer", device="cuda")
text = recognizer("audio.mp3", chunk_length_s=10, stride_length_s=(4, 2))["text"]

Training and evaluation data

25.79% WER (Eval with 10% of OpenSLR seed: 42)

{
  "epoch": 14.634146341463415,
  "eval_loss": 0.36365753412246704,
  "eval_runtime": 8.7546,
  "eval_samples_per_second": 33.24,
  "eval_steps_per_second": 4.226,
  "eval_wer": 0.2579008973858759,
  "step": 2400
}

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 15

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.0.1
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
11
Safetensors
Model size
606M params
Tensor type
F32
ยท
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for seanghay/w2v-bert-2.0-khmer

Finetuned
(228)
this model

Dataset used to train seanghay/w2v-bert-2.0-khmer

Space using seanghay/w2v-bert-2.0-khmer 1