| Kazakh model trained from https://github.com/IS2AI/ISSAI_SAIDA_Kazakh_ASR | |
| Thanks to | |
| A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline | |
| Yerbolat Khassanov, Saida Mussakhojayeva, Almas Mirzakhmetov, Alen Adiyev, Mukhamet Nurpeiissov, Huseyin Atakan Varol | |
| https://arxiv.org/abs/2009.10334 | |
| See also | |
| A baseline model for computationally inexpensive speech recognition for Kazakh using the Coqui STT framework | |
| Ilnar Salimzianov | |
| https://arxiv.org/abs/2107.10637 | |
| WER: | |
| %WER 8.06 [ 2844 / 35275, 437 ins, 358 del, 2049 sub ] exp/chain_a/tdnn/decode_dev_rescore/wer_10_0.0 | |
| %WER 6.81 [ 2444 / 35884, 309 ins, 398 del, 1737 sub ] exp/chain_a/tdnn/decode_test_rescore/wer_10_1.0 | |