101 Commits

Author	SHA1	Message	Date
Rino	e12fe350f5	Merge branch 'SWivid:main' into main	2024-11-01 17:44:04 +07:00
Yushen CHEN	b664bc7777	Update finetune_gradio.py	2024-11-01 18:20:39 +08:00
Yushen CHEN	552c0fd99c	Update prepare_csv_wavs.py	2024-11-01 18:17:57 +08:00
unknown	27d98a52cd	clear pipe	2024-11-01 12:08:47 +02:00
lpscr	9984a48041	Merge branch 'SWivid:main' into main	2024-11-01 12:06:52 +02:00
unknown	199c56c23c	clear pipe	2024-11-01 12:05:12 +02:00
unknown	f7a698bc2f	resample when need	2024-11-01 11:39:06 +02:00
unknown	5af195f1f9	only mono duraction fix value bfp16 to bf16	2024-11-01 11:18:05 +02:00
Rino	db902761c3	Update socket.py ... [remove] unused var	2024-11-01 15:14:52 +07:00
Rino	e8f14072ec	Merge branch 'SWivid:main' into main	2024-11-01 15:06:49 +07:00
SWivid	2a3deaab33	fix. update tgt_sr def for log_sample with new mel_spec module	2024-11-01 15:42:19 +08:00
SWivid	315230210d	minor fix	2024-11-01 15:11:48 +08:00
Yushen CHEN	305e3eab35	Merge pull request #345 from ZhikangNiu/main ... [WIP]Support Bigvgan vocoder	2024-11-01 14:37:30 +08:00
ZhikangNiu	18e1ab508f	refactor: del global params and set vocos as default vocoder, add dtype check	2024-11-01 14:17:22 +08:00
Rino	8713de5ffe	Merge branch 'SWivid:main' into main	2024-11-01 13:11:20 +07:00
SWivid	7a6fb0eb4e	fix address #348	2024-11-01 14:09:41 +08:00
Rino	561c67387d	Update socket.py ... [edit] socket.py calling vocab, ckpt, ref audio	2024-11-01 11:22:03 +07:00
Rino Alfian	1c8fe499ef	Update README.md ... socket client realtime stream	2024-11-01 10:13:36 +07:00
Rino Alfian	1e3fac8f5e	[add] socket.py ... to play stream socket mode	2024-11-01 10:10:31 +07:00
ZhikangNiu	b180961782	refactor: more details about bigvgan, clear function definition	2024-11-01 11:02:39 +08:00
ZhikangNiu	36a4aad668	change some infer function to support two vocoder	2024-10-31 22:44:45 +08:00
ZhikangNiu	712d52772e	update Bigvgan vocoder and F5-bigvgan version, trained on Emilia ZH&EN, 1.25m updates	2024-10-31 20:06:36 +08:00
Yushen CHEN	6cbb548f9c	Update api.py	2024-10-31 11:39:23 +08:00
unknown	3dd59b8cdf	when ref_text empty automatic transcribing	2024-10-30 14:26:13 +02:00
unknown	02d59131c4	fix when none tts_api	2024-10-30 14:25:16 +02:00
unknown	9c4fc38fa4	fix	2024-10-30 12:23:02 +02:00
unknown	77620f602f	suport more format	2024-10-30 11:41:42 +02:00
unknown	6970556abf	fix logger in settings miss	2024-10-30 11:21:47 +02:00
unknown	513e6b466e	add note for more format	2024-10-30 11:14:39 +02:00
unknown	9eb0d1d226	add to suport audio name , audio.wav , full audio path , add note	2024-10-30 11:09:22 +02:00
unknown	e9419764d7	add to suport audio name , audio.wav , full audio path	2024-10-30 11:03:26 +02:00
SWivid	aaa92f6e6d	finish trainer modification	2024-10-30 03:57:09 +08:00
SWivid	87c4f9ff06	minor fix	2024-10-30 03:23:22 +08:00
SWivid	381ea0c82c	fix vocoder loading	2024-10-30 03:16:09 +08:00
SWivid	da1b40968a	basic structure	2024-10-30 02:38:58 +08:00
SWivid	5b10099d33	Merge branch 'main' of github.com:lpscr/F5-TTS into lpscr-main	2024-10-29 23:36:58 +08:00
unknown	0be49f4967	flip axis y in mel	2024-10-29 17:35:42 +02:00
SWivid	2ccfbdcc61	Merge branch 'main' of github.com:lpscr/F5-TTS into lpscr-main	2024-10-29 23:34:00 +08:00
unknown	d5c307b56a	add logger	2024-10-29 17:30:28 +02:00
unknown	8a5041ef9f	update	2024-10-29 17:14:03 +02:00
unknown	886500ac97	update	2024-10-29 17:02:21 +02:00
unknown	2ca1fb7c25	update	2024-10-29 16:46:38 +02:00
unknown	3409192662	update	2024-10-29 16:44:23 +02:00
unknown	37eb3b50da	add tensorboard and add export sample for mel and audio	2024-10-29 14:20:50 +02:00
J	6667d6f501	Add optional text chat function	2024-10-29 10:59:42 +00:00
Jarod Mica	d601a70ad1	Revert "." ... This reverts commit 5089dfe51b.	2024-10-29 03:25:02 -07:00
Jarod Mica	5089dfe51b	.	2024-10-29 09:48:17 +00:00
SWivid	551857b268	minor fix.	2024-10-29 13:40:40 +08:00
SWivid	91881841dd	fix. wider search for silence	2024-10-29 13:26:55 +08:00
SWivid	82d04be12a	Update infer README.md	2024-10-29 13:18:04 +08:00