metadata
language:
- km
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- openslr
- google/fleurs
- seanghay/km-speech-corpus
metrics:
- wer
model-index:
- name: Whisper Small Khmer Spaced - Seanghay Yath
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Google FLEURS
type: google/fleurs
config: km_kh
split: test
metrics:
- name: Wer
type: wer
value: 0.6165
library_name: transformers
pipeline_tag: automatic-speech-recognition
whisper-small-khmer-v2
This model is a fine-tuned version of openai/whisper-small on the openslr, google/fleurs and km-speech-corpus dataset.
It achieves the following results on the evaluation set:
- Loss: 0.26
- Wer: 0.6165
Model description
This model is fine-tuned with Google FLEURS, OpenSLR (SLR42) and km-speech-corpus dataset.
from transformers import pipeline
pipe = pipeline(
task="automatic-speech-recognition",
model="seanghay/whisper-small-khmer-v2",
)
result = pipe("audio.wav",
generate_kwargs={
"language":"<|km|>",
"task":"transcribe"},
batch_size=16
)
print(result["text"])