| { | |
| "english": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-en-us-0.15", | |
| "vosk_model_language": "en", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip", | |
| "vosk_model_size": "1.8G", | |
| "vosk_model_word_error_rate_and_speed": "9.85 (librispeech test-clean) 10.38 (tedlium)", | |
| "vosk_model_notes": "Lightweight wideband model for Android and RPi ", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-en-us-0.22", | |
| "vosk_model_language": "en", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-en-us-0.22.zip", | |
| "vosk_model_size": "40M", | |
| "vosk_model_word_error_rate_and_speed": "5.69 (librispeech test-clean) 6.05 (tedlium) 29.78(callcenter)", | |
| "vosk_model_notes": "Accurate generic US English model", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-en-us-0.22-lgraph", | |
| "vosk_model_language": "en", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-en-us-0.22-lgraph.zip", | |
| "vosk_model_size": "128M", | |
| "vosk_model_word_error_rate_and_speed": "7.82 (librispeech) 8.20 (tedlium)", | |
| "vosk_model_notes": "Big US English model with dynamic graph", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-en-us-0.42-gigaspeech", | |
| "vosk_model_language": "en", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-en-us-0.42-gigaspeech.zip", | |
| "vosk_model_size": "2.3G", | |
| "vosk_model_word_error_rate_and_speed": "5.64 (librispeech test-clean) 6.24 (tedlium) 30.17 (callcenter)", | |
| "vosk_model_notes": "Accurate generic US English model trained by Kaldi on Gigaspeech. Mostly for podcasts, not for telephony", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-en-in-0.5", | |
| "vosk_model_language": "en-indian", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-en-in-0.5.zip", | |
| "vosk_model_size": "1G", | |
| "vosk_model_word_error_rate_and_speed": "36.12 (NPTEL Pure)", | |
| "vosk_model_notes": "Generic Indian English model for telecom and broadcast", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-small-en-in-0.4", | |
| "vosk_model_language": "en-indian", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-en-in-0.4.zip", | |
| "vosk_model_size": "36M", | |
| "vosk_model_word_error_rate_and_speed": "49.05 (NPTEL Pure)", | |
| "vosk_model_notes": "Lightweight Indian English model for mobile applications", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "chinese": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-cn-0.22", | |
| "vosk_model_language": "cn", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-cn-0.22.zip", | |
| "vosk_model_size": "42M", | |
| "vosk_model_word_error_rate_and_speed": "23.54 (SpeechIO-02) 38.29 (SpeechIO-06) 17.15 (THCHS)", | |
| "vosk_model_notes": "Lightweight model for Android and RPi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-cn-0.22", | |
| "vosk_model_language": "cn", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-cn-0.22.zip", | |
| "vosk_model_size": "1.3G", | |
| "vosk_model_word_error_rate_and_speed": "13.98 (SpeechIO-02) 27.30 (SpeechIO-06) 7.43 (THCHS)", | |
| "vosk_model_notes": "Big generic Chinese model for server processing", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-cn-kaldi-multicn-0.15", | |
| "vosk_model_language": "cn", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-cn-kaldi-multicn-0.15.zip", | |
| "vosk_model_size": "1.5G", | |
| "vosk_model_word_error_rate_and_speed": "17.44 (SpeechIO-02) 9.56 (THCHS)", | |
| "vosk_model_notes": "Original Wideband Kaldi multi-cn model from Kaldi with Vosk LM", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "french": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-fr-0.22", | |
| "vosk_model_language": "fr", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-fr-0.22.zip", | |
| "vosk_model_size": "41M", | |
| "vosk_model_word_error_rate_and_speed": "23.95 (cv test) 19.30 (mtedx) 27.25 (podcast)", | |
| "vosk_model_notes": "Lightweight wideband model for Android/iOS and RPi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-fr-0.22", | |
| "vosk_model_language": "fr", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-fr-0.22.zip", | |
| "vosk_model_size": "1.4G", | |
| "vosk_model_word_error_rate_and_speed": "14.72 (cv test) 11.64 (mls) 13.10 (mtedx) 21.61 (podcast) 13.22 (voxpopuli)", | |
| "vosk_model_notes": "Big accurate model for servers", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "spanish": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-es-0.42", | |
| "vosk_model_language": "es", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-es-0.42.zip", | |
| "vosk_model_size": "39M", | |
| "vosk_model_word_error_rate_and_speed": "16.02 (cv test) 16.72 (mtedx test) 11.21 (mls)", | |
| "vosk_model_notes": "Lightweight wideband model for Android/iOS and RPi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-es-0.42", | |
| "vosk_model_language": "es", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-es-0.42.zip", | |
| "vosk_model_size": "1.4G", | |
| "vosk_model_word_error_rate_and_speed": "7.50 (cv test) 10.05 (mtedx test) 5.84 (mls)", | |
| "vosk_model_notes": "Big model for Spanish", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "german": [ | |
| { | |
| "vosk_model_id": "vosk-model-de-0.21", | |
| "vosk_model_language": "de", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-de-0.21.zip", | |
| "vosk_model_size": "1.9G", | |
| "vosk_model_word_error_rate_and_speed": "9.83 (Tuda-de test), 24.00 (podcast) 12.82 (cv-test) 12.42 (mls) 33.26 (mtedx)", | |
| "vosk_model_notes": "Big German model for telephony and server", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-small-de-zamia-0.3", | |
| "vosk_model_language": "de", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-de-zamia-0.3.zip", | |
| "vosk_model_size": "1.4G", | |
| "vosk_model_word_error_rate_and_speed": "14.81 (Tuda-de test, 37.46 (podcast)", | |
| "vosk_model_notes": "Zamia f_250 small model repackaged (not recommended)", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-small-de-0.15", | |
| "vosk_model_language": "de", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-de-zamia-0.3.zip", | |
| "vosk_model_size": "45M", | |
| "vosk_model_word_error_rate_and_speed": "13.75 (Tuda-de test), 30.67 (podcast)", | |
| "vosk_model_notes": "Lightweight wideband model for Android and RPi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "portuguese": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-pt-0.3", | |
| "vosk_model_language": "pt", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-pt-0.3.zip", | |
| "vosk_model_size": "1.9G", | |
| "vosk_model_word_error_rate_and_speed": "68.92 (coraa dev) 32.60 (cv test)", | |
| "vosk_model_notes": "Lightweight wideband model for Android and RPi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-pt-fb-v0.1.1-20220516_2113", | |
| "vosk_model_language": "pt", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-pt-fb-v0.1.1-20220516_2113.zip", | |
| "vosk_model_size": "1.6G", | |
| "vosk_model_word_error_rate_and_speed": "54.34 (coraa dev) 27.70 (cv test)", | |
| "vosk_model_notes": "Big model from FalaBrazil", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "greek": [ | |
| { | |
| "vosk_model_id": "vosk-model-el-gr-0.7", | |
| "vosk_model_language": "gr", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-el-gr-0.7.zip", | |
| "vosk_model_size": "1.1G", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Big narrowband Greek model for server processing, not extremely accurate though", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "vietnamese": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-vn-0.4", | |
| "vosk_model_language": "vn", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-vn-0.4.zip", | |
| "vosk_model_size": "32M", | |
| "vosk_model_word_error_rate_and_speed": "15.70 (Vivos test)", | |
| "vosk_model_notes": "Lightweight Vietnamese model", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-vn-0.4", | |
| "vosk_model_language": "vn", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-vn-0.4.zip", | |
| "vosk_model_size": "78M", | |
| "vosk_model_word_error_rate_and_speed": "15.70 (Vivos test)", | |
| "vosk_model_notes": "Bigger Vietnamese model for server", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "italian": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-it-0.22", | |
| "vosk_model_language": "it", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-it-0.22.zip", | |
| "vosk_model_size": "48M", | |
| "vosk_model_word_error_rate_and_speed": "16.88 (cv test) 25.87 (mls) 17.01 (mtedx)", | |
| "vosk_model_notes": "Lightweight model for Android and RPi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-it-0.22", | |
| "vosk_model_language": "it", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-vn-0.4.zip", | |
| "vosk_model_size": "1.2G", | |
| "vosk_model_word_error_rate_and_speed": "8.10 (cv test) 15.68 (mls) 11.23 (mtedx)", | |
| "vosk_model_notes": "Big generic Italian model for servers", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "dutch": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-nl-0.22", | |
| "vosk_model_language": "nl", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-nl-0.22.zip", | |
| "vosk_model_size": "39M", | |
| "vosk_model_word_error_rate_and_speed": "22.45 (cv test) 26.80 (tv) 25.84 (mls) 24.09 (voxpopuli)", | |
| "vosk_model_notes": "Lightweight model for Dutch", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "arabic": [ | |
| { | |
| "vosk_model_id": "vosk-model-ar-mgb2-0.4", | |
| "vosk_model_language": "ar", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-ar-mgb2-0.4.zip", | |
| "vosk_model_size": "318M", | |
| "vosk_model_word_error_rate_and_speed": "16.40 (MGB-2 dev set)", | |
| "vosk_model_notes": "Repackaged Arabic model trained on MGB2 dataset from Kaldi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-ar-0.22-linto-1.1.0", | |
| "vosk_model_language": "ar", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-ar-0.22-linto-1.1.0.zip", | |
| "vosk_model_size": "1.3G", | |
| "vosk_model_word_error_rate_and_speed": "16.40 (MGB-2 dev set)", | |
| "vosk_model_notes": "52.87 (cv test) 28.50 (MBG-2 dev set) 1.0xRT", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "farsi": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-fa-0.4", | |
| "vosk_model_language": "ph", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-fa-0.4.zip", | |
| "vosk_model_size": "47M", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Lightweight wideband model for Android and RPi for Farsi (Persian)", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-fa-0.5", | |
| "vosk_model_language": "ph", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-fa-0.5.zip", | |
| "vosk_model_size": "1G", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Model with large vocabulary, not yet accurate but better than before (Persian)", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "filipino": [ | |
| { | |
| "vosk_model_id": "vosk-model-tl-ph-generic-0.6", | |
| "vosk_model_language": "ph", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-tl-ph-generic-0.6.zip", | |
| "vosk_model_size": "320M", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Medium wideband model for Filipino (Tagalog) by feddybear", | |
| "vosk_model_licenses": "CC-BY-NC-SA 4.0" | |
| } | |
| ], | |
| "ukrainian": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-uk-v3-small", | |
| "vosk_model_language": "uk", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-uk-v3-small.zip", | |
| "vosk_model_size": "133M", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Small model from Speech Recognition for Ukrainian", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-uk-v3", | |
| "vosk_model_language": "uk", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-uk-v3.zip", | |
| "vosk_model_size": "343M", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Bigger model from Speech Recognition for Ukrainian", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "swedish": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-sv-rhasspy-0.15", | |
| "vosk_model_language": "sv", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-sv-rhasspy-0.15.zip", | |
| "vosk_model_size": "289M", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Repackaged model from Rhasspy project", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "japanese": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-ja-0.22", | |
| "vosk_model_language": "ja", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-ja-0.22.zip", | |
| "vosk_model_size": "48M", | |
| "vosk_model_word_error_rate_and_speed": "9.52(csj CER) 17.07(ted10k CER)", | |
| "vosk_model_notes": "Lightweight wideband model for Japanese", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-ja-0.22", | |
| "vosk_model_language": "ja", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-ja-0.22.zip", | |
| "vosk_model_size": "1Gb", | |
| "vosk_model_word_error_rate_and_speed": "8.40(csj CER) 13.91(ted10k CER)", | |
| "vosk_model_notes": "Big model for Japanese", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "hindi": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-hi-0.22", | |
| "vosk_model_language": "hi", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-hi-0.22.zip", | |
| "vosk_model_size": "42M", | |
| "vosk_model_word_error_rate_and_speed": "20.89 (IITM Challenge) 24.72 (MUCS Challenge)", | |
| "vosk_model_notes": "Lightweight model for Hindi", | |
| "vosk_model_licenses": "Apache 2.0" | |
| }, | |
| { | |
| "vosk_model_id": "vosk-model-hi-0.22", | |
| "vosk_model_language": "hi", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-hi-0.22.zip", | |
| "vosk_model_size": "1.5Gb", | |
| "vosk_model_word_error_rate_and_speed": "14.85 (CV Test) 14.83 (IITM Challenge) 13.11 (MUCS Challenge)", | |
| "vosk_model_notes": "Big accurate model for servers", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "czech": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-cs-0.4-rhasspy", | |
| "vosk_model_language": "cs", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-cs-0.4-rhasspy.zip", | |
| "vosk_model_size": "44M", | |
| "vosk_model_word_error_rate_and_speed": "21.29 (CV Test)", | |
| "vosk_model_notes": "Lightweight model for Czech from Rhasspy project", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "polish": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-pl-0.22", | |
| "vosk_model_language": "pl", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-pl-0.22.zip", | |
| "vosk_model_size": "50M", | |
| "vosk_model_word_error_rate_and_speed": "18.36 (CV Test) 16.88 (MLS Test) 11.55 (Voxpopuli Test)", | |
| "vosk_model_notes": "Lightweight model for Polish", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "uzbek": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-uz-0.22", | |
| "vosk_model_language": "uz", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-uz-0.22.zip", | |
| "vosk_model_size": "82M", | |
| "vosk_model_word_error_rate_and_speed": "13.54 (CV Test) 12.92 (IS2AI USC test)", | |
| "vosk_model_notes": "Lightweight model for Uzbek", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "korean": [ | |
| { | |
| "vosk_model_id": "vosk-model-small-ko-0.22", | |
| "vosk_model_language": "ko", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-small-ko-0.22.zip", | |
| "vosk_model_size": "82M", | |
| "vosk_model_word_error_rate_and_speed": "28.1 (Zeroth Test)", | |
| "vosk_model_notes": "Lightweight model for Korean", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ], | |
| "speaker_identification": [ | |
| { | |
| "vosk_model_id": "vosk-model-spk-0.4", | |
| "vosk_model_language": "TBD", | |
| "vosk_model_file_url": "https://alphacephei.com/vosk/models/vosk-model-spk-0.4.zip", | |
| "vosk_model_size": "13M", | |
| "vosk_model_word_error_rate_and_speed": "TBD", | |
| "vosk_model_notes": "Model for speaker identification, should work for all languages", | |
| "vosk_model_licenses": "Apache 2.0" | |
| } | |
| ] | |
| } |