diff --git a/samples/en/en_US/bryce/medium/MODEL_CARD b/samples/en/en_US/bryce/medium/MODEL_CARD new file mode 100644 index 0000000..cb4671d --- /dev/null +++ b/samples/en/en_US/bryce/medium/MODEL_CARD @@ -0,0 +1,16 @@ +# Model card for bryce (medium) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* License: public domain + +## Training + +See: https://brycebeattie.com/files/tts/ + +US English male voice. Single Speaker. Finetuned for an additional 1000 epochs from an unreleased voice which had 2500 epochs. This is my voice, I only recorded about 750 samples. diff --git a/samples/en/en_US/bryce/medium/sample.txt b/samples/en/en_US/bryce/medium/sample.txt new file mode 100644 index 0000000..b0a2cf8 --- /dev/null +++ b/samples/en/en_US/bryce/medium/sample.txt @@ -0,0 +1 @@ +A rainbow is a meteorological phenomenon that is caused by reflection, refraction and dispersion of light in water droplets resulting in a spectrum of light appearing in the sky. diff --git a/samples/en/en_US/bryce/medium/speaker_0.mp3 b/samples/en/en_US/bryce/medium/speaker_0.mp3 new file mode 100644 index 0000000..94057b0 Binary files /dev/null and b/samples/en/en_US/bryce/medium/speaker_0.mp3 differ diff --git a/samples/en/en_US/john/medium/MODEL_CARD b/samples/en/en_US/john/medium/MODEL_CARD new file mode 100644 index 0000000..6f590d3 --- /dev/null +++ b/samples/en/en_US/john/medium/MODEL_CARD @@ -0,0 +1,17 @@ +# Model card for john (medium) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://librivox.org +* License: public domain + +## Training + +See: https://brycebeattie.com/files/tts/ + +US English male voice. Single Speaker. Finetuned from Kristin (above) on medium quality settings for an additional 600 epochs. I put together the dataset, which ended up with about 12.5 hours of recordings. All recordings came from LibriVox.org. diff --git a/samples/en/en_US/john/medium/sample.txt b/samples/en/en_US/john/medium/sample.txt new file mode 100644 index 0000000..b0a2cf8 --- /dev/null +++ b/samples/en/en_US/john/medium/sample.txt @@ -0,0 +1 @@ +A rainbow is a meteorological phenomenon that is caused by reflection, refraction and dispersion of light in water droplets resulting in a spectrum of light appearing in the sky. diff --git a/samples/en/en_US/john/medium/speaker_0.mp3 b/samples/en/en_US/john/medium/speaker_0.mp3 new file mode 100644 index 0000000..16c756b Binary files /dev/null and b/samples/en/en_US/john/medium/speaker_0.mp3 differ diff --git a/samples/en/en_US/norman/medium/MODEL_CARD b/samples/en/en_US/norman/medium/MODEL_CARD new file mode 100644 index 0000000..0c932c8 --- /dev/null +++ b/samples/en/en_US/norman/medium/MODEL_CARD @@ -0,0 +1,17 @@ +# Model card for norman (medium) + +* Language: en_US (English, United States) +* Speakers: 1 +* Quality: medium +* Samplerate: 22,050Hz + +## Dataset + +* URL: https://librivox.org +* License: public domain + +## Training + +See: https://brycebeattie.com/files/tts/ + +US English male voice. Single Speaker. Trained from scratch on medium quality settings for 1200 epochs. I put together the dataset, which ended up with about 15.5 hours of recordings. All recordings came from LibriVox.org. I forgot to save the ckpt file on this one, sorry. diff --git a/samples/en/en_US/norman/medium/sample.txt b/samples/en/en_US/norman/medium/sample.txt new file mode 100644 index 0000000..b0a2cf8 --- /dev/null +++ b/samples/en/en_US/norman/medium/sample.txt @@ -0,0 +1 @@ +A rainbow is a meteorological phenomenon that is caused by reflection, refraction and dispersion of light in water droplets resulting in a spectrum of light appearing in the sky. diff --git a/samples/en/en_US/norman/medium/speaker_0.mp3 b/samples/en/en_US/norman/medium/speaker_0.mp3 new file mode 100644 index 0000000..60dcbcd Binary files /dev/null and b/samples/en/en_US/norman/medium/speaker_0.mp3 differ diff --git a/voices.json b/voices.json index 6b1d648..9972075 100644 --- a/voices.json +++ b/voices.json @@ -1436,6 +1436,36 @@ }, "aliases": [] }, + "en_US-bryce-medium": { + "key": "en_US-bryce-medium", + "name": "bryce", + "language": { + "code": "en_US", + "family": "en", + "region": "US", + "name_native": "English", + "name_english": "English", + "country_english": "United States" + }, + "quality": "medium", + "num_speakers": 1, + "speaker_id_map": {}, + "files": { + "en/en_US/bryce/medium/en_US-bryce-medium.onnx": { + "size_bytes": 63531379, + "md5_digest": "a8482817c3bdc3d20121a0e31bfa9809" + }, + "en/en_US/bryce/medium/en_US-bryce-medium.onnx.json": { + "size_bytes": 4966, + "md5_digest": "a548d1d4ce8579f5a16926bdec77c7bf" + }, + "en/en_US/bryce/medium/MODEL_CARD": { + "size_bytes": 405, + "md5_digest": "79f21fcb165d0fcc4680222164bbb569" + } + }, + "aliases": [] + }, "en_US-danny-low": { "key": "en_US-danny-low", "name": "danny", @@ -1556,6 +1586,36 @@ }, "aliases": [] }, + "en_US-john-medium": { + "key": "en_US-john-medium", + "name": "john", + "language": { + "code": "en_US", + "family": "en", + "region": "US", + "name_native": "English", + "name_english": "English", + "country_english": "United States" + }, + "quality": "medium", + "num_speakers": 1, + "speaker_id_map": {}, + "files": { + "en/en_US/john/medium/en_US-john-medium.onnx": { + "size_bytes": 63531379, + "md5_digest": "70480857f21f2560f3a232722023b36d" + }, + "en/en_US/john/medium/en_US-john-medium.onnx.json": { + "size_bytes": 4965, + "md5_digest": "f2d04611b498e14d394385d1ec8a2d2d" + }, + "en/en_US/john/medium/MODEL_CARD": { + "size_bytes": 498, + "md5_digest": "4ef938585cf2cc8da4ada9b6d2c579ec" + } + }, + "aliases": [] + }, "en_US-kathleen-low": { "key": "en_US-kathleen-low", "name": "kathleen", @@ -3729,6 +3789,36 @@ }, "aliases": [] }, + "en_US-norman-medium": { + "key": "en_US-norman-medium", + "name": "norman", + "language": { + "code": "en_US", + "family": "en", + "region": "US", + "name_native": "English", + "name_english": "English", + "country_english": "United States" + }, + "quality": "medium", + "num_speakers": 1, + "speaker_id_map": {}, + "files": { + "en/en_US/norman/medium/en_US-norman-medium.onnx": { + "size_bytes": 63531379, + "md5_digest": "829cea515dc724d694b83b71e8083f9f" + }, + "en/en_US/norman/medium/en_US-norman-medium.onnx.json": { + "size_bytes": 4968, + "md5_digest": "975830d6f230f6eccf657d265de99eba" + }, + "en/en_US/norman/medium/MODEL_CARD": { + "size_bytes": 528, + "md5_digest": "c34f20bbc4918681ad7a070a8321f2fa" + } + }, + "aliases": [] + }, "en_US-ryan-high": { "key": "en_US-ryan-high", "name": "ryan", @@ -4751,8 +4841,8 @@ "md5_digest": "3a44e73b12ca5d0c21a72e388b5847c8" }, "it/it_IT/paola/medium/it_IT-paola-medium.onnx.json": { - "size_bytes": 7100, - "md5_digest": "3c983f7292518f042b4d137b2dfe65b3" + "size_bytes": 7099, + "md5_digest": "cd471a3757c88a7a4baee6207248b5d5" }, "it/it_IT/paola/medium/MODEL_CARD": { "size_bytes": 303,