m3hrdadfi
/

wav2vec2-base-100k-gtzan-music-genres

Automatic Speech Recognition

audio-classification

Inference Endpoints

Model card Files Files and versions Community

wav2vec2-base-100k-gtzan-music-genres / train_results.json

m3hrdadfi's picture

Initial model

0ee0f25 over 3 years ago

154 Bytes

	{
	"epoch": 20.0,
	"train_runtime": 7059.2772,
	"train_samples": 799,
	"train_samples_per_second": 2.264,
	"train_steps_per_second": 1.13
	}