jonatasgrosman's picture
jonatasgrosman/exp_w2v2t_zh-cn_unispeech-sat_s496
145ddbc
metadata
language:
  - zh-CN
license: apache-2.0
tags:
  - automatic-speech-recognition
  - zh-CN
datasets:
  - mozilla-foundation/common_voice_7_0

exp_w2v2t_zh-cn_unispeech-sat_s496

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

This model has been fine-tuned by the HuggingSound tool.