PereLluis13
/

wav2vec2-xls-r-300m-ca-lm

Automatic Speech Recognition Transformers PyTorch TensorBoard

Catalan wav2vec2 collectivat/tv3_parla generated_from_trainer hf-asr-leaderboard mozilla-foundation/common_voice_8_0 projecte-aina/parlament_parla robust-speech-event Eval Results Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

wav2vec2-xls-r-300m-ca-lm / preprocessor_config.json

PereLluis13's picture

add LM model version

8c7b5cc about 2 years ago

raw history blame contribute delete

No virus

260 Bytes

	{
	"do_normalize": true,
	"feature_extractor_type": "Wav2Vec2FeatureExtractor",
	"feature_size": 1,
	"padding_side": "right",
	"padding_value": 0,
	"processor_class": "Wav2Vec2ProcessorWithLM",
	"return_attention_mask": true,
	"sampling_rate": 16000
	}