Mirrors/VoiceCraft
1
0
Fork 0
mirror of https://github.com/jasonppy/VoiceCraft.git synced 2026-04-08 12:18:38 +02:00
Code Issues Packages Projects Releases Wiki Activity

upload TTS finetuned 330M model

Browse Source
This commit is contained in:
jason-on-salt-a40
2024-04-05 16:42:59 -07:00
parent bae982eb15
commit 142772c3df
2 changed files with 21 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
inference_tts.ipynb
View File

@@ -63,7 +63,7 @@
"device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
"from models import voicecraft\n",
"#import models.voicecraft as voicecraft\n",
"voicecraft_name=\"giga830M.pth\" # or giga330M.pth\n",
"voicecraft_name=\"gigaHalfLibri330M_TTSEnhanced_max16s.pth\" # or giga330M.pth, giga830M.pth\n",
"ckpt_fn =f\"./pretrained_models/{voicecraft_name}\"\n",
"encodec_fn = \"./pretrained_models/encodec_4cb2048_giga.th\"\n",
"if not os.path.exists(ckpt_fn):\n",
@@ -141,14 +141,14 @@
"codec_audio_sr = 16000\n",
"codec_sr = 50\n",
"top_k = 0\n",
"top_p = 0.8\n",
"top_p = 0.9 # can also try 0.8, but 0.9 seems to work better\n",
"temperature = 1\n",
"silence_tokens=[1388,1898,131]\n",
"kvcache = 1 # NOTE if OOM, change this to 0, or try the 330M model\n",
"\n",
"# NOTE adjust the below three arguments if the generation is not as good\n",
"stop_repetition = 3 # NOTE if the model generate long silence, reduce the stop_repetition to 3, 2 or even 1\n",
"sample_batch_size = 4 # NOTE: if the if there are long silence or unnaturally strecthed words, increase sample_batch_size to 5 or higher. What this will do to the model is that the model will run sample_batch_size examples of the same audio, and pick the one that's the shortest. So if the speech rate of the generated is too fast change it to a smaller number.\n",
"sample_batch_size = 2 # for gigaHalfLibri330M_TTSEnhanced_max16s.pth, 1 or 2 should be fine since the model is trained to do TTS, for the other two models, might need a higher number. NOTE: if the if there are long silence or unnaturally strecthed words, increase sample_batch_size to 5 or higher. What this will do to the model is that the model will run sample_batch_size examples of the same audio, and pick the one that's the shortest. So if the speech rate of the generated is too fast change it to a smaller number.\n",
"seed = 1 # change seed if you are still unhappy with the result\n",
"\n",
"def seed_everything(seed):\n",