diff --git a/README.md b/README.md index 3d9976e..a0a9eb0 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ This repository tracks releases of open models for 🐸STT. - | Language | Creator | Release | |----------|---------|---------| -| [Ukrainian](https://en.wikipedia.org/wiki/Ukrainian_language) | [Yurii Paniv](https://github.com/robinhad/) | [`0.4`](https://github.com/coqui-ai/STT-models/releases/ukrainian/robinhad/0.4) | \ No newline at end of file +| [Ukrainian](https://en.wikipedia.org/wiki/Ukrainian_language) | [Yurii Paniv](https://github.com/robinhad/) | [`v0.4`](https://github.com/coqui-ai/STT-models/releases/tag/ukrainian/robinhad/v0.4) | +| [Welsh](https://en.wikipedia.org/wiki/Welsh_language) | [Dewi Bryn Jones](https://github.com/dewibrynjones/) | [`v21.03`](https://github.com/coqui-ai/STT-models/releases/tag/welsh/techiaith/v21.03) | \ No newline at end of file diff --git a/catalan/ccoreilly/MODEL_CARD.md b/catalan/ccoreilly/MODEL_CARD.md index 65f5f55..0fa109b 100644 --- a/catalan/ccoreilly/MODEL_CARD.md +++ b/catalan/ccoreilly/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Github](https://github.com/ccoreilly/deepspeech-catala/releases/tag/0.14.0) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.14.0` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [deepspeech-catala](https://github.com/ccoreilly/deepspeech-catala) - License: MIT - Citation details: `@misc{catalan-ccoreilly, @@ -82,7 +83,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/french/commonvoice-fr/MODEL_CARD.md b/french/commonvoice-fr/MODEL_CARD.md index f0220da..0ea7b85 100644 --- a/french/commonvoice-fr/MODEL_CARD.md +++ b/french/commonvoice-fr/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Github](https://github.com/common-voice/commonvoice-fr/releases/tag/fr-v0.6) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.6` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [commonvoice-fr](https://github.com/common-voice/commonvoice-fr) - License: MPL 2.0 - Citation details: `@misc{commonvoice-fr, @@ -101,7 +102,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/french/jaco-polyglot/MODEL_CARD.md b/french/jaco-polyglot/MODEL_CARD.md index 8c6c5d7..2cfeea0 100644 --- a/french/jaco-polyglot/MODEL_CARD.md +++ b/french/jaco-polyglot/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Gitlab](https://gitlab.com/Jaco-Assistant/Scribosermo) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.0.1` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [scribosermo](https://gitlab.com/Jaco-Assistant/Scribosermo/-/tree/master/#old-experiments) - License: GNU Lesser General Public License - Citation details: `@misc{french-jaco, @@ -80,7 +81,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/german/aashishag/MODEL_CARD.md b/german/aashishag/MODEL_CARD.md index bb354b8..bf6ca05 100644 --- a/german/aashishag/MODEL_CARD.md +++ b/german/aashishag/MODEL_CARD.md @@ -17,16 +17,17 @@ Jump to section: - Model date: Accessed from [deepspeech-german](https://github.com/AASHISHAG/deepspeech-german) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.9.0` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [deepspeech-german](https://github.com/AASHISHAG/deepspeech-german) - License: Apache 2.0 - Citation details: `@inproceedings{agarwal-zesch-2019-german, - author = "Aashish Agarwal and Torsten Zesch", - title = "German End-to-end Speech Recognition based on DeepSpeech", - booktitle = "Preliminary proceedings of the 15th Conference on Natural Language Processing (KONVENS 2019): Long Papers", - year = "2019", - address = "Erlangen, Germany", - publisher = "German Society for Computational Linguistics \& Language Technology", - pages = "111--119" +author = "Aashish Agarwal and Torsten Zesch", +title = "German End-to-end Speech Recognition based on DeepSpeech", +booktitle = "Preliminary proceedings of the 15th Conference on Natural Language Processing (KONVENS 2019): Long Papers", +year = "2019", +address = "Erlangen, Germany", +publisher = "German Society for Computational Linguistics \& Language Technology", +pages = "111--119" }` - Where to send questions or comments about the model: You can leave an issue on [`STT-model` issues](https://github.com/coqui-ai/STT-models/issues), open a new discussion on [`STT-model` discussions](https://github.com/coqui-ai/STT-models/discussions), or chat with us on [Gitter](https://gitter.im/coqui-ai/). @@ -77,7 +78,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/german/jaco-polyglot/MODEL_CARD.md b/german/jaco-polyglot/MODEL_CARD.md index 6eb6eb1..f329b36 100644 --- a/german/jaco-polyglot/MODEL_CARD.md +++ b/german/jaco-polyglot/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Gitlab](https://gitlab.com/Jaco-Assistant/Scribosermo) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.0.1` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [scribosermo](https://gitlab.com/Jaco-Assistant/Scribosermo/-/tree/master/#old-experiments) - License: GNU Lesser General Public License - Citation details: `@misc{german-jaco, @@ -82,7 +83,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/italian/jaco-polyglot/MODEL_CARD.md b/italian/jaco-polyglot/MODEL_CARD.md index 4e2fa89..3e2e033 100644 --- a/italian/jaco-polyglot/MODEL_CARD.md +++ b/italian/jaco-polyglot/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Gitlab](https://gitlab.com/Jaco-Assistant/Scribosermo) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.0.1` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [scribosermo](https://gitlab.com/Jaco-Assistant/Scribosermo/-/tree/master/#old-experiments) - License: GNU Lesser General Public License - Citation details: `@misc{italian-jaco, @@ -80,7 +81,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/kinyarwanda/digital-umuganda/MODEL_CARD.md b/kinyarwanda/digital-umuganda/MODEL_CARD.md index 6e9ae35..9173023 100644 --- a/kinyarwanda/digital-umuganda/MODEL_CARD.md +++ b/kinyarwanda/digital-umuganda/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Github](https://github.com/Digital-Umuganda/Deepspeech-Kinyarwanda/tree/master/jan-8-2021-best-kinya-deepspeech) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.0.1` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [deepspeech-kinyarwanda](https://github.com/Digital-Umuganda/Deepspeech-Kinyarwanda) - License: MPL 2.0 - Citation details: `@misc{deepspeech-kinyarwanda, @@ -78,7 +79,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/komi/itml/MODEL_CARD.md b/komi/itml/MODEL_CARD.md index 4437160..9243540 100644 --- a/komi/itml/MODEL_CARD.md +++ b/komi/itml/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.0.1` +- Compatible with 🐸 STT version: `v0.9.3` - License: AGPL - Citation details: `@inproceedings{hjortnaes-etal-2020-towards, title = "Towards a Speech Recognizer for {K}omi, an Endangered and Low-Resource Uralic Language", @@ -82,7 +83,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/polish/jaco-polyglot/MODEL_CARD.md b/polish/jaco-polyglot/MODEL_CARD.md index 767690f..efdb984 100644 --- a/polish/jaco-polyglot/MODEL_CARD.md +++ b/polish/jaco-polyglot/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Gitlab](https://gitlab.com/Jaco-Assistant/Scribosermo) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.0.1` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [scribosermo](https://gitlab.com/Jaco-Assistant/Scribosermo/-/tree/master/#old-experiments) - License: GNU Lesser General Public License - Citation details: `@misc{polish-jaco, @@ -80,7 +81,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/spanish/jaco-polyglot/MODEL_CARD.md b/spanish/jaco-polyglot/MODEL_CARD.md index 577b14a..0f5f7cc 100644 --- a/spanish/jaco-polyglot/MODEL_CARD.md +++ b/spanish/jaco-polyglot/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Gitlab](https://gitlab.com/Jaco-Assistant/Scribosermo) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.0.1` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [scribosermo](https://gitlab.com/Jaco-Assistant/Scribosermo/-/tree/master/#old-experiments) - License: GNU Lesser General Public License - Citation details: `@misc{spanish-jaco, @@ -80,7 +81,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/ukrainian/robinhad/MODEL_CARD.md b/ukrainian/robinhad/MODEL_CARD.md index e132bbe..f341030 100644 --- a/ukrainian/robinhad/MODEL_CARD.md +++ b/ukrainian/robinhad/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Github](https://github.com/robinhad/voice-recognition-ua/releases/tag/v0.4) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v0.4` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [voice-recognition-ua](https://github.com/robinhad/voice-recognition-ua) - License: CC BY-NC 4.0 - Citation details: `@misc{ukrainian-stt-paniv, @@ -80,7 +81,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech. diff --git a/welsh/techiaith/MODEL_CARD.md b/welsh/techiaith/MODEL_CARD.md index 5dc34ea..79005dd 100644 --- a/welsh/techiaith/MODEL_CARD.md +++ b/welsh/techiaith/MODEL_CARD.md @@ -17,6 +17,7 @@ Jump to section: - Model date: Accessed from [Github](https://github.com/techiaith/docker-deepspeech-cy/releases/tag/21.03) on March 31, 2021 - Model type: `Speech-to-Text` - Model version: `v21.03` +- Compatible with 🐸 STT version: `v0.9.3` - Code: [docker-deepspeech-cy](https://github.com/techiaith/docker-deepspeech-cy) - License: MIT - Citation details: `@misc{welsh-stt-dewibrynjones, @@ -75,7 +76,7 @@ Deploying a Speech-to-Text model into any production setting has ethical implica You should assume every machine learning model has demographic bias unless proven otherwise. For STT models, it is often the case that transcription accuracy is better for men than it is for women. If you are using this model in production, you should acknowledge this as a potential issue. -### Surveillence +### Surveillance Speech-to-Text may be mis-used to invade the privacy of others by recording and mining information from private conversations. This kind of individual privacy is protected by law in may countries. You should not assume consent to record and analyze private speech.