ivanlau
/

wav2vec2-large-xls-r-300m-cantonese

Automatic Speech Recognition Transformers PyTorch

Chinese wav2vec2 generated_from_trainer hf-asr-leaderboard mozilla-foundation/common_voice_8_0 robust-speech-event zh-HK Eval Results Inference Endpoints

Model card Files Files and versions Community

wav2vec2-large-xls-r-300m-cantonese / eval_results.json

ivanlau's picture

End of training

45d3667 about 2 years ago

raw history blame contribute delete

No virus

225 Bytes

	{
	"epoch": 100.0,
	"eval_loss": 1.484755277633667,
	"eval_runtime": 166.9526,
	"eval_samples": 3659,
	"eval_samples_per_second": 21.916,
	"eval_steps_per_second": 1.372,
	"eval_wer": 0.8004362050163577
	}