Automatic Speech Recognition
Transformers
Safetensors
whisper
Inference Endpoints
JackyHoCL's picture
Update README.md
e713994 verified
|
raw
history blame
513 Bytes
metadata
library_name: transformers
license: mit
datasets:
  - AlienKevin/mixed_cantonese_and_english_speech
  - mozilla-foundation/common_voice_17_0
metrics:
  - cer
base_model:
  - openai/whisper-large-v3-turbo

CER: 15.2%

transformers-4.46.3

Train Args:
per_device_train_batch_size=16,
gradient_accumulation_steps=1,
learning_rate=2e-5,
gradient_checkpointing=True,
per_device_eval_batch_size=16,
generation_max_length=225,

Hardware:
NVIDIA Tesla V100 16GB * 4