8000 Transcribe: New language models by viren-nadkarni · Pull Request #12336 · localstack/localstack · GitHub
[go: up one dir, main page]

Skip to content

Transcribe: New language models #12336

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Mar 13, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 28 additions & 17 deletions localstack-core/localstack/services/transcribe/provider.py
55C7
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
BadRequestException,
ConflictException,
GetTranscriptionJobResponse,
8000 LanguageCode,
ListTranscriptionJobsResponse,
MaxResults,
MediaFormat,
Expand Down Expand Up @@ -47,24 +48,34 @@

VOSK_MODELS_URL = f"{HUGGING_FACE_ENDPOINT}/vosk-models/resolve/main/"

# Map of language codes to language models
# Map of language codes to Vosk language models
# See https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html
LANGUAGE_MODELS = {
"en-IN": "vosk-model-small-en-in-0.4",
"en-US": "vosk-model-small-en-us-0.15",
"en-GB": "vosk-model-small-en-gb-0.15",
"fr-FR": "vosk-model-small-fr-0.22",
"de-DE": "vosk-model-small-de-0.15",
"es-ES": "vosk-model-small-es-0.22",
"it-IT": "vosk-model-small-it-0.4",
"pt-BR": "vosk-model-small-pt-0.3",
"ru-RU": "vosk-model-small-ru-0.4",
"nl-NL": "vosk-model-small-nl-0.22",
"tr-TR": "vosk-model-small-tr-0.3",
"hi-IN": "vosk-model-small-hi-0.22",
"ja-JP": "vosk-model-small-ja-0.22",
"fa-IR": "vosk-model-small-fa-0.5",
"vi-VN": "vosk-model-small-vn-0.3",
"zh-CN": "vosk-model-small-cn-0.3",
LanguageCode.ca_ES: "vosk-model-small-ca-0.4",
LanguageCode.cs_CZ: "vosk-model-small-cs-0.4-rhasspy",
LanguageCode.en_GB: "vosk-model-small-en-gb-0.15",
LanguageCode.en_IN: "vosk-model-small-en-in-0.4",
LanguageCode.en_US: "vosk-model-small-en-us-0.15",
LanguageCode.fa_IR: "vosk-model-small-fa-0.42",
LanguageCode.fr_FR: "vosk-model-small-fr-0.22",
LanguageCode.de_DE: "vosk-model-small-de-0.15",
LanguageCode.es_ES: "vosk-model-small-es-0.42",
LanguageCode.gu_IN: "vosk-model-small-gu-0.42",
LanguageCode.hi_IN: "vosk-model-small-hi-0.22",
LanguageCode.it_IT: "vosk-model-small-it-0.22",
LanguageCode.ja_JP: "vosk-model-small-ja-0.22",
LanguageCode.kk_KZ: "vosk-model-small-kz-0.15",
LanguageCode.ko_KR: "vosk-model-small-ko-0.22",
LanguageCode.nl_NL: "vosk-model-small-nl-0.22",
LanguageCode.pl_PL: "vosk-model-small-pl-0.22",
LanguageCode.pt_BR: "vosk-model-small-pt-0.3",
LanguageCode.ru_RU: "vosk-model-small-ru-0.22",
LanguageCode.te_IN: "vosk-model-small-te-0.42",
LanguageCode.tr_TR: "vosk-model-small-tr-0.3",
LanguageCode.uk_UA: "vosk-model-small-uk-v3-nano",
LanguageCode.uz_UZ: "vosk-model-small-uz-0.22",
LanguageCode.vi_VN: "vosk-model-small-vn-0.4",
LanguageCode.zh_CN: "vosk-model-small-cn-0.22",
}

LANGUAGE_MODEL_DIR = Path(config.dirs.cache) / "vosk"
Expand Down
Loading
0