ttsds/openvoice_2 📝❓🖼️ → 🖼️

▶️ 784 runs 📅 Jan 2025 ⚙️ Cog 0.13.6

About

Example Output

Output

Performance Metrics

7.36s Prediction Time

60.62s Total Time

All Input Parameters

{
  "text": "With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.",
  "language": "en",
  "speaker_reference": "https://replicate.delivery/pbxt/MNFXdPaUPOwYCZjZM4azsymbzE2TCV2WJXfGpeV2DrFWaSq8/example_en.wav"
}

Input Parameters

text (required) Type: string
language (required)
speaker_reference (required) Type: string

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

OpenVoice version: v2
/root/.pyenv/versions/3.10.16/lib/python3.10/site-packages/torch/hub.py:267: UserWarning: You are about to download and run code from an untrusted repository. In a future release, this won't be allowed. To add the repository to your trusted list, change the command to {calling_fn}(..., trust_repo=False) and a command prompt will appear asking for an explicit confirmation of trust, or load(..., trust_repo=True), which will assume that the prompt is to be answered with 'yes'. You can also use load(..., trust_repo='check') which will only prompt for confirmation if the repo is not already trusted. This will eventually be the default behaviour
warnings.warn(
Downloading: "https://github.com/snakers4/silero-vad/zipball/master" to /root/.cache/torch/hub/master.zip
[(0.0, 3.4)]
after vad: dur = 3.4
> Text split to sentences.
With tenure, Suzie'd have all the more leisure for yachting, but her publications are no good.
> ===========================
  0%|          | 0/1 [00:00<?, ?it/s]
Downloading pytorch_model.bin:   0%|          | 0.00/440M [00:00<?, ?B/s][A
Downloading pytorch_model.bin:   7%|▋         | 31.5M/440M [00:00<00:01, 230MB/s][A
Downloading pytorch_model.bin:  14%|█▍        | 62.9M/440M [00:00<00:01, 240MB/s][A
Downloading pytorch_model.bin:  21%|██▏       | 94.4M/440M [00:00<00:01, 232MB/s][A
Downloading pytorch_model.bin:  29%|██▊       | 126M/440M [00:00<00:01, 231MB/s] [A
Downloading pytorch_model.bin:  36%|███▌      | 157M/440M [00:00<00:01, 229MB/s][A
Downloading pytorch_model.bin:  43%|████▎     | 189M/440M [00:00<00:01, 224MB/s][A
Downloading pytorch_model.bin:  50%|████▉     | 220M/440M [00:00<00:00, 228MB/s][A
Downloading pytorch_model.bin:  57%|█████▋    | 252M/440M [00:01<00:00, 231MB/s][A
Downloading pytorch_model.bin:  64%|██████▍   | 283M/440M [00:01<00:00, 226MB/s][A
Downloading pytorch_model.bin:  71%|███████▏  | 315M/440M [00:01<00:00, 227MB/s][A
Downloading pytorch_model.bin:  79%|███████▊  | 346M/440M [00:01<00:00, 230MB/s][A
Downloading pytorch_model.bin:  86%|████████▌ | 377M/440M [00:01<00:00, 232MB/s][A
Downloading pytorch_model.bin:  93%|█████████▎| 409M/440M [00:01<00:00, 231MB/s][A
Downloading pytorch_model.bin: 100%|█████████▉| 440M/440M [00:01<00:00, 228MB/s][A
Downloading pytorch_model.bin: 100%|██████████| 440M/440M [00:01<00:00, 229MB/s]
Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForMaskedLM: ['cls.seq_relationship.weight', 'cls.seq_relationship.bias']
- This IS expected if you are initializing BertForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
100%|██████████| 1/1 [00:04<00:00,  4.15s/it]
100%|██████████| 1/1 [00:04<00:00,  4.15s/it]

Version Details

Version ID: 795fe9c3fc9d3d4cfac1ca97d8c8d33b522b42068daec53ab3c74f775dd506c8
Version Created: January 31, 2025

Run on Replicate →