Branches

mirror of https://github.com/coqui-ai/TTS.git synced 2026-02-24 12:10:16 +01:00

dev

dbf1a08a0d · Update generic_utils.py (#3561) · Updated 2024-02-10 15:20:58 +01:00

dev-yourtts-rec 4a94f3ae31 · Add Original YourTTS vocabulary for full transfer learning · Updated 2022-12-12 16:31:02 +01:00 Mirrors	493 6	ZIP TAR.GZ
update-workflows 6f59d45caa · Update dep caching in actions · Updated 2022-11-09 11:56:20 +01:00 Mirrors	519 1	ZIP TAR.GZ
fix_comp_emb 89c6e2a32f · Add paramter for eval meta file on compute embeddings script · Updated 2022-09-21 18:59:13 +02:00 Mirrors	531 1	ZIP TAR.GZ
dev-update-readme 91b2dbd7a9 · Add YourTTS and SC-GlowTTS on available models · Updated 2022-09-02 19:59:31 +02:00 Mirrors	545 1	ZIP TAR.GZ
fix_bce_loss 5fee6ca355 · Remove import · Updated 2022-08-15 10:49:01 +02:00 Mirrors	555 2	ZIP TAR.GZ
dev-emotion-rebased 5e6bd601d0 · Ignore NaN embeddings on the compute embeddings script · Updated 2022-07-04 19:56:41 +02:00 Mirrors	592 63	ZIP TAR.GZ
fix-publish 66ccb7488e · Fix version checking · Updated 2022-06-30 13:54:08 +02:00 Mirrors	584 17	ZIP TAR.GZ
emotion-dataset 602ca85c74 · Fix pred_avg_pitch_emb · Updated 2022-06-28 14:37:54 +02:00 Mirrors	592 60	ZIP TAR.GZ
vits-pitch-pred-new 85ce5aee34 · Remove Pitch conditioning on encoder · Updated 2022-06-23 18:34:39 +02:00 Mirrors	592 57	ZIP TAR.GZ
attribute-extraction dca929cea4 · Added d-vector pool selection implementation · Updated 2022-06-23 13:52:23 +02:00 Mirrors	591 4	ZIP TAR.GZ
fix_condition_dp_on_speaker a969a11c04 · Fix condition_dp_on_speaker · Updated 2022-06-18 14:03:46 +02:00 Mirrors	591 10	ZIP TAR.GZ
emotion_cond_module bf45319f64 · Add speaker and emotion squeezer layers · Updated 2022-06-07 14:27:08 +02:00 Mirrors	599 40	ZIP TAR.GZ
add-synpaflex-formatter 4a5143679d · Make style · Updated 2022-06-02 14:44:21 +02:00 Mirrors	594 3	ZIP TAR.GZ
d_vector_serialization d7de111b76 · Change default speakers file extension · Updated 2022-06-01 10:31:26 +02:00 Mirrors	596 8	ZIP TAR.GZ
thorsten_models f7b75e880d · Add Thorsten VITS model · Updated 2022-05-31 15:10:04 +02:00 Mirrors	595 1	ZIP TAR.GZ
dev-emotion 63d27bc8d4 · Disable the reversal prosody encoder speaker loss · Updated 2022-05-19 15:55:14 +02:00 Mirrors	644 40	ZIP TAR.GZ
vits-pitch-pred bdefc43d96 · Bug fix on pre-compute F0 · Updated 2022-05-19 15:48:02 +02:00 Mirrors	644 40	ZIP TAR.GZ
unified_api_forwardtts2 8adcd1de8e · Rename `g` as `spk_emb` · Updated 2022-05-17 13:47:06 +02:00 Mirrors	601 32	ZIP TAR.GZ
audio_len_sampler 002f826a1c · Add unit tests · Updated 2022-05-12 19:11:48 +02:00 Mirrors	606 2	ZIP TAR.GZ
cpu-only-docker-image 5e4bd9bfe8 · Merge branch 'cpu-only-docker-image' of https://github.com/coqui-ai/TTS into cpu-only-docker-image · Updated 2022-05-12 18:50:06 +02:00 Mirrors	606 5	ZIP TAR.GZ

1 2 3 4

Default Branch