lucataco/whisperspeech-small 📝❓ → 🖼️

▶️ 1.6K runs 📅 Jan 2024 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
text-to-speech voice-cloning

About

An Open Source text-to-speech system built by inverting Whisper

Example Output

Prompt:

"This is the first demo of Whisper Speech, a fully open source text-to-speech model trained by Collabora and Lion on the Juwels supercomputer"

Output

Example output

Performance Metrics

24.50s Prediction Time
145.56s Total Time
All Input Parameters 
{
  "prompt": "This is the first demo of Whisper Speech, a fully open source text-to-speech model trained by Collabora and Lion on the Juwels supercomputer",
  "speaker": "",
  "language": "en"
}
Input Parameters
prompt Type: stringDefault: This is the first demo of Whisper Speech, a fully open source text-to-speech model trained by Collabora and Lion on the Juwels supercomputer.
Text to synthesize
speaker Type: stringDefault:
URL for zero-shot voice cloning(ex: https://upload.wikimedia.org/wikipedia/commons/7/75/Winston_Churchill_-_Be_Ye_Men_of_Valour.ogg)
language Default: en
Language to synthesize
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
█
|----------------------------------------| 0.00% [0/749 00:00<?]
|----------------------------------------| 0.13% [1/749 00:00<00:18]
|----------------------------------------| 0.27% [2/749 00:00<00:14]
|----------------------------------------| 0.40% [3/749 00:00<00:13]
|----------------------------------------| 0.53% [4/749 00:00<00:13]
|----------------------------------------| 0.67% [5/749 00:00<00:12]
|----------------------------------------| 2.14% [16/749 00:00<00:11]
|█---------------------------------------| 3.74% [28/749 00:00<00:11]
|██--------------------------------------| 5.34% [40/749 00:00<00:10]
|██--------------------------------------| 6.94% [52/749 00:00<00:10]
|███-------------------------------------| 8.54% [64/749 00:00<00:10]
|████------------------------------------| 10.15% [76/749 00:01<00:10]
|████------------------------------------| 11.75% [88/749 00:01<00:10]
|█████-----------------------------------| 13.35% [100/749 00:01<00:09]
|█████-----------------------------------| 14.95% [112/749 00:01<00:09]
|██████----------------------------------| 16.56% [124/749 00:01<00:09]
|███████---------------------------------| 18.16% [136/749 00:02<00:09]
|███████---------------------------------| 19.76% [148/749 00:02<00:09]
|████████--------------------------------| 21.36% [160/749 00:02<00:09]
|█████████-------------------------------| 22.96% [172/749 00:02<00:08]
|█████████-------------------------------| 24.57% [184/749 00:02<00:08]
|██████████------------------------------| 26.17% [196/749 00:03<00:08]
|███████████-----------------------------| 27.77% [208/749 00:03<00:08]
|███████████-----------------------------| 29.37% [220/749 00:03<00:08]
|████████████----------------------------| 30.97% [232/749 00:03<00:07]
|█████████████---------------------------| 32.58% [244/749 00:03<00:07]
█
|----------------------------------------| 0.00% [0/752 00:00<?]
|----------------------------------------| 0.13% [1/752 00:00<00:19]
|----------------------------------------| 0.27% [2/752 00:00<00:19]
|----------------------------------------| 0.40% [3/752 00:00<00:19]
|----------------------------------------| 0.53% [4/752 00:00<00:19]
|----------------------------------------| 0.66% [5/752 00:00<00:19]
|----------------------------------------| 1.60% [12/752 00:00<00:19]
|█---------------------------------------| 2.53% [19/752 00:00<00:18]
|█---------------------------------------| 3.46% [26/752 00:00<00:18]
 |█---------------------------------------| 4.39% [33/752 00:00<00:18]
|██--------------------------------------| 5.32% [40/752 00:01<00:18]
|██--------------------------------------| 6.25% [47/752 00:01<00:17]
|██--------------------------------------| 7.18% [54/752 00:01<00:17]
|███-------------------------------------| 8.11% [61/752 00:01<00:17]
|███-------------------------------------| 9.04% [68/752 00:01<00:17]
|███-------------------------------------| 9.97% [75/752 00:01<00:17]
|████------------------------------------| 10.90% [82/752 00:02<00:16]
|████------------------------------------| 11.84% [89/752 00:02<00:16]
|█████-----------------------------------| 12.77% [96/752 00:02<00:16]
|█████-----------------------------------| 13.70% [103/752 00:02<00:16]
|█████-----------------------------------| 14.63% [110/752 00:02<00:16]
|██████----------------------------------| 15.56% [117/752 00:02<00:16]
|██████----------------------------------| 16.49% [124/752 00:03<00:15]
|██████----------------------------------| 17.42% [131/752 00:03<00:15]
|███████---------------------------------| 18.35% [138/752 00:03<00:15]
|███████---------------------------------| 19.28% [145/752 00:03<00:15]
|████████--------------------------------| 20.21% [152/752 00:03<00:15]
|████████--------------------------------| 21.14% [159/752 00:04<00:15]
|████████--------------------------------| 22.07% [166/752 00:04<00:14]
|█████████-------------------------------| 23.01% [173/752 00:04<00:14]
|█████████-------------------------------| 23.94% [180/752 00:04<00:14]
|█████████-------------------------------| 24.87% [187/752 00:04<00:14]
|██████████------------------------------| 25.80% [194/752 00:04<00:14]
|██████████------------------------------| 26.73% [201/752 00:05<00:13]
|███████████-----------------------------| 27.66% [208/752 00:05<00:13]
|███████████-----------------------------| 28.59% [215/752 00:05<00:13]
|███████████-----------------------------| 29.52% [222/752 00:05<00:13]
|████████████----------------------------| 30.45% [229/752 00:05<00:13]
|████████████----------------------------| 31.38% [236/752 00:06<00:13]
|████████████----------------------------| 32.31% [243/752 00:06<00:12]
|█████████████---------------------------| 33.24% [250/752 00:06<00:12]
|█████████████---------------------------| 34.18% [257/752 00:06<00:12]
|██████████████--------------------------| 35.11% [264/752 00:06<00:12]
|██████████████--------------------------| 36.04% [271/752 00:06<00:12]
|██████████████--------------------------| 36.97% [278/752 00:07<00:12]
|███████████████-------------------------| 37.90% [285/752 00:07<00:11]
|███████████████-------------------------| 38.83% [292/752 00:07<00:11]
|███████████████-------------------------| 39.76% [299/752 00:07<00:11]
|████████████████------------------------| 40.69% [306/752 00:07<00:11]
|████████████████------------------------| 41.62% [313/752 00:08<00:11]
|█████████████████-----------------------| 42.55% [320/752 00:08<00:11]
|█████████████████-----------------------| 43.48% [327/752 00:08<00:10]
|█████████████████-----------------------| 44.41% [334/752 00:08<00:10]
|██████████████████----------------------| 45.35% [341/752 00:08<00:10]
|██████████████████----------------------| 46.28% [348/752 00:08<00:10]
|██████████████████----------------------| 47.21% [355/752 00:09<00:10]
|███████████████████---------------------| 48.14% [362/752 00:09<00:09]
|███████████████████---------------------| 49.07% [369/752 00:09<00:09]
|████████████████████--------------------| 50.00% [376/752 00:09<00:09]
|████████████████████--------------------| 50.93% [383/752 00:09<00:09]
|████████████████████--------------------| 51.86% [390/752 00:09<00:09]
|█████████████████████-------------------| 52.79% [397/752 00:10<00:09]
|█████████████████████-------------------| 53.72% [404/752 00:10<00:08]
|█████████████████████-------------------| 54.65% [411/752 00:10<00:08]
|██████████████████████------------------| 55.59% [418/752 00:10<00:08]
|██████████████████████------------------| 56.52% [425/752 00:10<00:08]
|██████████████████████------------------| 57.45% [432/752 00:11<00:08]
|███████████████████████-----------------| 58.38% [439/752 00:11<00:08]
|███████████████████████-----------------| 59.31% [446/752 00:11<00:07]
|████████████████████████----------------| 60.24% [453/752 00:11<00:07]
|████████████████████████----------------| 61.17% [460/752 00:11<00:07]
|████████████████████████----------------| 62.10% [467/752 00:11<00:07]
|█████████████████████████---------------| 63.03% [474/752 00:12<00:07]
|█████████████████████████---------------| 63.96% [481/752 00:12<00:06]
|█████████████████████████---------------| 64.89% [488/752 00:12<00:06]
|██████████████████████████--------------| 65.82% [495/752 00:12<00:06]
|██████████████████████████--------------| 66.76% [502/752 00:12<00:06]
|███████████████████████████-------------| 67.69% [509/752 00:12<00:06]
|███████████████████████████-------------| 68.62% [516/752 00:13<00:06]
|███████████████████████████-------------| 69.55% [523/752 00:13<00:05]
|████████████████████████████------------| 70.48% [530/752 00:13<00:05]
|████████████████████████████------------| 71.41% [537/752 00:13<00:05]
|████████████████████████████------------| 72.34% [544/752 00:13<00:05]
|█████████████████████████████-----------| 73.27% [551/752 00:14<00:05]
|█████████████████████████████-----------| 74.20% [558/752 00:14<00:04]
|██████████████████████████████----------| 75.13% [565/752 00:14<00:04]
|██████████████████████████████----------| 76.06% [572/752 00:14<00:04]
|██████████████████████████████----------| 76.99% [579/752 00:14<00:04]
|███████████████████████████████---------| 77.93% [586/752 00:14<00:04]
|███████████████████████████████---------| 78.86% [593/752 00:15<00:04]
|███████████████████████████████---------| 79.79% [600/752 00:15<00:03]
|████████████████████████████████--------| 80.72% [607/752 00:15<00:03]
|████████████████████████████████--------| 81.65% [614/752 00:15<00:03]
|█████████████████████████████████-------| 82.58% [621/752 00:15<00:03]
|█████████████████████████████████-------| 83.51% [628/752 00:15<00:03]
|█████████████████████████████████-------| 84.44% [635/752 00:16<00:02]
|██████████████████████████████████------| 85.37% [642/752 00:16<00:02]
|██████████████████████████████████------| 86.30% [649/752 00:16<00:02]
|██████████████████████████████████------| 87.23% [656/752 00:16<00:02]
|███████████████████████████████████-----| 88.16% [663/752 00:16<00:02]
|███████████████████████████████████-----| 89.10% [670/752 00:17<00:02]
|████████████████████████████████████----| 90.03% [677/752 00:17<00:01]
|████████████████████████████████████----| 90.96% [684/752 00:17<00:01]
|████████████████████████████████████----| 91.89% [691/752 00:17<00:01]
|█████████████████████████████████████---| 92.82% [698/752 00:17<00:01]
|█████████████████████████████████████---| 93.75% [705/752 00:17<00:01]
|█████████████████████████████████████---| 94.68% [712/752 00:18<00:01]
|██████████████████████████████████████--| 95.61% [719/752 00:18<00:00]
|██████████████████████████████████████--| 96.54% [726/752 00:18<00:00]
|██████████████████████████████████████--| 97.47% [733/752 00:18<00:00]
|███████████████████████████████████████-| 98.40% [740/752 00:18<00:00]
|███████████████████████████████████████-| 99.34% [747/752 00:18<00:00]
|████████████████████████████████████████| 100.00% [752/752 00:19<00:00]
Version Details
Version ID
70789b0c0bfa6d81964a43545867f34a8f8175572c429e7c3c2869fb6fa5ff95
Version Created
January 18, 2024
Run on Replicate →