jonatasgrosman

exp_w2v2t_ja_unispeech_s253

jonatasgrosman/exp_w2v2t_ja_unispeech_s253

exp_w2v2t_ja_unispeech_s253 is a automatic speech recognition model from jonatasgrosman. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.

Fine-tuned microsoft/unispeech-large-1500h-cv for speech recognition using the train split of Common Voice 7.0 (ja). When using this model, make sure that your speech input is sampled at 16kHz.