What to do with models that come with a .index file? #469

New Issue

cjohnson · 2024-01-25T21:22:52Z

cjohnson commented

2024-01-25 21:22:52 +00:00

EDIT: Oh sorry, this model is for RVC. i'm an idiot. my bad.
Hi, I've got a voice model from https://voice-models.com/model/1o4sJQdShCc, and when I try to load it I get a bunch of errors.

Loading autoregressive model: ./models/finetunes/PRTL2-CaveJohnson-20231018-Batch8-40kHz_e388_s19788.pth Traceback (most recent call last): File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/gradio/routes.py", line 394, in run_predict output = await app.get_blocks().process_api( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1075, in process_api result = await self.call_function( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/gradio/blocks.py", line 884, in call_function prediction = await anyio.to_thread.run_sync( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread return await future File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, *args) File "/media/username/WD10BX/ai-voice-cloning/src/utils.py", line 3695, in reload_tts load_tts() File "/media/username/WD10BX/ai-voice-cloning/src/utils.py", line 3666, in load_tts tts = TorToise_TTS(minor_optimizations=not args.low_vram, autoregressive_model_path=autoregressive_model, diffusion_model_path=diffusion_model, vocoder_model=vocoder_model, tokenizer_json=tokenizer_json, unsqueeze_sample_batches=args.unsqueeze_sample_batches, use_deepspeed=args.use_deepspeed) File "/media/username/WD10BX/ai-voice-cloning/modules/tortoise-tts/tortoise/api.py", line 308, in __init__ self.load_autoregressive_model(autoregressive_model_path) File "/media/username/WD10BX/ai-voice-cloning/modules/tortoise-tts/tortoise/api.py", line 391, in load_autoregressive_model self.autoregressive.load_state_dict(torch.load(self.autoregressive_model_path)) File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for UnifiedVoice: Missing key(s) in state_dict: "conditioning_encoder.init.weight", "conditioning_encoder.init.bias", "conditioning_encoder.attn.0.norm.weight", "conditioning_encoder.attn.0.norm.bias", "conditioning_encoder.attn.0.qkv.weight", "conditioning_encoder.attn.0.qkv.bias", "conditioning_encoder.attn.0.proj_out.weight", "conditioning_encoder.attn.0.proj_out.bias", "conditioning_encoder.attn.1.norm.weight", "conditioning_encoder.attn.1.norm.bias", "conditioning_encoder.attn.1.qkv.weight", "conditioning_encoder.attn.1.qkv.bias", "conditioning_encoder.attn.1.proj_out.weight", "conditioning_encoder.attn.1.proj_out.bias", "conditioning_encoder.attn.2.norm.weight", "conditioning_encoder.attn.2.norm.bias", "conditioning_encoder.attn.2.qkv.weight", "conditioning_encoder.attn.2.qkv.bias", "conditioning_encoder.attn.2.proj_out.weight", "conditioning_encoder.attn.2.proj_out.bias", "conditioning_encoder.attn.3.norm.weight", "conditioning_encoder.attn.3.norm.bias", "conditioning_encoder.attn.3.qkv.weight", "conditioning_encoder.attn.3.qkv.bias", "conditioning_encoder.attn.3.proj_out.weight", "conditioning_encoder.attn.3.proj_out.bias", "conditioning_encoder.attn.4.norm.weight", "conditioning_encoder.attn.4.norm.bias", "conditioning_encoder.attn.4.qkv.weight", "conditioning_encoder.attn.4.qkv.bias", "conditioning_encoder.attn.4.proj_out.weight", "conditioning_encoder.attn.4.proj_out.bias", "conditioning_encoder.attn.5.norm.weight", "conditioning_encoder.attn.5.norm.bias", "conditioning_encoder.attn.5.qkv.weight", "conditioning_encoder.attn.5.qkv.bias", "conditioning_encoder.attn.5.proj_out.weight", "conditioning_encoder.attn.5.proj_out.bias", "text_embedding.weight", "mel_embedding.weight", "gpt.h.0.ln_1.weight", "gpt.h.0.ln_1.bias", "gpt.h.0.attn.bias", "gpt.h.0.attn.masked_bias", "gpt.h.0.attn.c_attn.weight", "gpt.h.0.attn.c_attn.bias", "gpt.h.0.attn.c_proj.weight", "gpt.h.0.attn.c_proj.bias", "gpt.h.0.ln_2.weight", "gpt.h.0.ln_2.bias", "gpt.h.0.mlp.c_fc.weight", "gpt.h.0.mlp.c_fc.bias", "gpt.h.0.mlp.c_proj.weight", "gpt.h.0.mlp.c_proj.bias", "gpt.h.1.ln_1.weight", "gpt.h.1.ln_1.bias", "gpt.h.1.attn.bias", "gpt.h.1.attn.masked_bias", "gpt.h.1.attn.c_attn.weight", "gpt.h.1.attn.c_attn.bias", "gpt.h.1.attn.c_proj.weight", "gpt.h.1.attn.c_proj.bias", "gpt.h.1.ln_2.weight", "gpt.h.1.ln_2.bias", "gpt.h.1.mlp.c_fc.weight", "gpt.h.1.mlp.c_fc.bias", "gpt.h.1.mlp.c_proj.weight", "gpt.h.1.mlp.c_proj.bias", "gpt.h.2.ln_1.weight", "gpt.h.2.ln_1.bias", "gpt.h.2.attn.bias", "gpt.h.2.attn.masked_bias", "gpt.h.2.attn.c_attn.weight", "gpt.h.2.attn.c_attn.bias", "gpt.h.2.attn.c_proj.weight", "gpt.h.2.attn.c_proj.bias", "gpt.h.2.ln_2.weight", "gpt.h.2.ln_2.bias", "gpt.h.2.mlp.c_fc.weight", "gpt.h.2.mlp.c_fc.bias", "gpt.h.2.mlp.c_proj.weight", "gpt.h.2.mlp.c_proj.bias", "gpt.h.3.ln_1.weight", "gpt.h.3.ln_1.bias", "gpt.h.3.attn.bias", "gpt.h.3.attn.masked_bias", "gpt.h.3.attn.c_attn.weight", "gpt.h.3.attn.c_attn.bias", "gpt.h.3.attn.c_proj.weight", "gpt.h.3.attn.c_proj.bias", "gpt.h.3.ln_2.weight", "gpt.h.3.ln_2.bias", "gpt.h.3.mlp.c_fc.weight", "gpt.h.3.mlp.c_fc.bias", "gpt.h.3.mlp.c_proj.weight", "gpt.h.3.mlp.c_proj.bias", "gpt.h.4.ln_1.weight", "gpt.h.4.ln_1.bias", "gpt.h.4.attn.bias", "gpt.h.4.attn.masked_bias", "gpt.h.4.attn.c_attn.weight", "gpt.h.4.attn.c_attn.bias", "gpt.h.4.attn.c_proj.weight", "gpt.h.4.attn.c_proj.bias", "gpt.h.4.ln_2.weight", "gpt.h.4.ln_2.bias", "gpt.h.4.mlp.c_fc.weight", "gpt.h.4.mlp.c_fc.bias", "gpt.h.4.mlp.c_proj.weight", "gpt.h.4.mlp.c_proj.bias", "gpt.h.5.ln_1.weight", "gpt.h.5.ln_1.bias", "gpt.h.5.attn.bias", "gpt.h.5.attn.masked_bias", "gpt.h.5.attn.c_attn.weight", "gpt.h.5.attn.c_attn.bias", "gpt.h.5.attn.c_proj.weight", "gpt.h.5.attn.c_proj.bias", "gpt.h.5.ln_2.weight", "gpt.h.5.ln_2.bias", "gpt.h.5.mlp.c_fc.weight", "gpt.h.5.mlp.c_fc.bias", "gpt.h.5.mlp.c_proj.weight", "gpt.h.5.mlp.c_proj.bias", "gpt.h.6.ln_1.weight", "gpt.h.6.ln_1.bias", "gpt.h.6.attn.bias", "gpt.h.6.attn.masked_bias", "gpt.h.6.attn.c_attn.weight", "gpt.h.6.attn.c_attn.bias", "gpt.h.6.attn.c_proj.weight", "gpt.h.6.attn.c_proj.bias", "gpt.h.6.ln_2.weight", "gpt.h.6.ln_2.bias", "gpt.h.6.mlp.c_fc.weight", "gpt.h.6.mlp.c_fc.bias", "gpt.h.6.mlp.c_proj.weight", "gpt.h.6.mlp.c_proj.bias", "gpt.h.7.ln_1.weight", "gpt.h.7.ln_1.bias", "gpt.h.7.attn.bias", "gpt.h.7.attn.masked_bias", "gpt.h.7.attn.c_attn.weight", "gpt.h.7.attn.c_attn.bias", "gpt.h.7.attn.c_proj.weight", "gpt.h.7.attn.c_proj.bias", "gpt.h.7.ln_2.weight", "gpt.h.7.ln_2.bias", "gpt.h.7.mlp.c_fc.weight", "gpt.h.7.mlp.c_fc.bias", "gpt.h.7.mlp.c_proj.weight", "gpt.h.7.mlp.c_proj.bias", "gpt.h.8.ln_1.weight", "gpt.h.8.ln_1.bias", "gpt.h.8.attn.bias", "gpt.h.8.attn.masked_bias", "gpt.h.8.attn.c_attn.weight", "gpt.h.8.attn.c_attn.bias", "gpt.h.8.attn.c_proj.weight", "gpt.h.8.attn.c_proj.bias", "gpt.h.8.ln_2.weight", "gpt.h.8.ln_2.bias", "gpt.h.8.mlp.c_fc.weight", "gpt.h.8.mlp.c_fc.bias", "gpt.h.8.mlp.c_proj.weight", "gpt.h.8.mlp.c_proj.bias", "gpt.h.9.ln_1.weight", "gpt.h.9.ln_1.bias", "gpt.h.9.attn.bias", "gpt.h.9.attn.masked_bias", "gpt.h.9.attn.c_attn.weight", "gpt.h.9.attn.c_attn.bias", "gpt.h.9.attn.c_proj.weight", "gpt.h.9.attn.c_proj.bias", "gpt.h.9.ln_2.weight", "gpt.h.9.ln_2.bias", "gpt.h.9.mlp.c_fc.weight", "gpt.h.9.mlp.c_fc.bias", "gpt.h.9.mlp.c_proj.weight", "gpt.h.9.mlp.c_proj.bias", "gpt.h.10.ln_1.weight", "gpt.h.10.ln_1.bias", "gpt.h.10.attn.bias", "gpt.h.10.attn.masked_bias", "gpt.h.10.attn.c_attn.weight", "gpt.h.10.attn.c_attn.bias", "gpt.h.10.attn.c_proj.weight", "gpt.h.10.attn.c_proj.bias", "gpt.h.10.ln_2.weight", "gpt.h.10.ln_2.bias", "gpt.h.10.mlp.c_fc.weight", "gpt.h.10.mlp.c_fc.bias", "gpt.h.10.mlp.c_proj.weight", "gpt.h.10.mlp.c_proj.bias", "gpt.h.11.ln_1.weight", "gpt.h.11.ln_1.bias", "gpt.h.11.attn.bias", "gpt.h.11.attn.masked_bias", "gpt.h.11.attn.c_attn.weight", "gpt.h.11.attn.c_attn.bias", "gpt.h.11.attn.c_proj.weight", "gpt.h.11.attn.c_proj.bias", "gpt.h.11.ln_2.weight", "gpt.h.11.ln_2.bias", "gpt.h.11.mlp.c_fc.weight", "gpt.h.11.mlp.c_fc.bias", "gpt.h.11.mlp.c_proj.weight", "gpt.h.11.mlp.c_proj.bias", "gpt.h.12.ln_1.weight", "gpt.h.12.ln_1.bias", "gpt.h.12.attn.bias", "gpt.h.12.attn.masked_bias", "gpt.h.12.attn.c_attn.weight", "gpt.h.12.attn.c_attn.bias", "gpt.h.12.attn.c_proj.weight", "gpt.h.12.attn.c_proj.bias", "gpt.h.12.ln_2.weight", "gpt.h.12.ln_2.bias", "gpt.h.12.mlp.c_fc.weight", "gpt.h.12.mlp.c_fc.bias", "gpt.h.12.mlp.c_proj.weight", "gpt.h.12.mlp.c_proj.bias", "gpt.h.13.ln_1.weight", "gpt.h.13.ln_1.bias", "gpt.h.13.attn.bias", "gpt.h.13.attn.masked_bias", "gpt.h.13.attn.c_attn.weight", "gpt.h.13.attn.c_attn.bias", "gpt.h.13.attn.c_proj.weight", "gpt.h.13.attn.c_proj.bias", "gpt.h.13.ln_2.weight", "gpt.h.13.ln_2.bias", "gpt.h.13.mlp.c_fc.weight", "gpt.h.13.mlp.c_fc.bias", "gpt.h.13.mlp.c_proj.weight", "gpt.h.13.mlp.c_proj.bias", "gpt.h.14.ln_1.weight", "gpt.h.14.ln_1.bias", "gpt.h.14.attn.bias", "gpt.h.14.attn.masked_bias", "gpt.h.14.attn.c_attn.weight", "gpt.h.14.attn.c_attn.bias", "gpt.h.14.attn.c_proj.weight", "gpt.h.14.attn.c_proj.bias", "gpt.h.14.ln_2.weight", "gpt.h.14.ln_2.bias", "gpt.h.14.mlp.c_fc.weight", "gpt.h.14.mlp.c_fc.bias", "gpt.h.14.mlp.c_proj.weight", "gpt.h.14.mlp.c_proj.bias", "gpt.h.15.ln_1.weight", "gpt.h.15.ln_1.bias", "gpt.h.15.attn.bias", "gpt.h.15.attn.masked_bias", "gpt.h.15.attn.c_attn.weight", "gpt.h.15.attn.c_attn.bias", "gpt.h.15.attn.c_proj.weight", "gpt.h.15.attn.c_proj.bias", "gpt.h.15.ln_2.weight", "gpt.h.15.ln_2.bias", "gpt.h.15.mlp.c_fc.weight", "gpt.h.15.mlp.c_fc.bias", "gpt.h.15.mlp.c_proj.weight", "gpt.h.15.mlp.c_proj.bias", "gpt.h.16.ln_1.weight", "gpt.h.16.ln_1.bias", "gpt.h.16.attn.bias", "gpt.h.16.attn.masked_bias", "gpt.h.16.attn.c_attn.weight", "gpt.h.16.attn.c_attn.bias", "gpt.h.16.attn.c_proj.weight", "gpt.h.16.attn.c_proj.bias", "gpt.h.16.ln_2.weight", "gpt.h.16.ln_2.bias", "gpt.h.16.mlp.c_fc.weight", "gpt.h.16.mlp.c_fc.bias", "gpt.h.16.mlp.c_proj.weight", "gpt.h.16.mlp.c_proj.bias", "gpt.h.17.ln_1.weight", "gpt.h.17.ln_1.bias", "gpt.h.17.attn.bias", "gpt.h.17.attn.masked_bias", "gpt.h.17.attn.c_attn.weight", "gpt.h.17.attn.c_attn.bias", "gpt.h.17.attn.c_proj.weight", "gpt.h.17.attn.c_proj.bias", "gpt.h.17.ln_2.weight", "gpt.h.17.ln_2.bias", "gpt.h.17.mlp.c_fc.weight", "gpt.h.17.mlp.c_fc.bias", "gpt.h.17.mlp.c_proj.weight", "gpt.h.17.mlp.c_proj.bias", "gpt.h.18.ln_1.weight", "gpt.h.18.ln_1.bias", "gpt.h.18.attn.bias", "gpt.h.18.attn.masked_bias", "gpt.h.18.attn.c_attn.weight", "gpt.h.18.attn.c_attn.bias", "gpt.h.18.attn.c_proj.weight", "gpt.h.18.attn.c_proj.bias", "gpt.h.18.ln_2.weight", "gpt.h.18.ln_2.bias", "gpt.h.18.mlp.c_fc.weight", "gpt.h.18.mlp.c_fc.bias", "gpt.h.18.mlp.c_proj.weight", "gpt.h.18.mlp.c_proj.bias", "gpt.h.19.ln_1.weight", "gpt.h.19.ln_1.bias", "gpt.h.19.attn.bias", "gpt.h.19.attn.masked_bias", "gpt.h.19.attn.c_attn.weight", "gpt.h.19.attn.c_attn.bias", "gpt.h.19.attn.c_proj.weight", "gpt.h.19.attn.c_proj.bias", "gpt.h.19.ln_2.weight", "gpt.h.19.ln_2.bias", "gpt.h.19.mlp.c_fc.weight", "gpt.h.19.mlp.c_fc.bias", "gpt.h.19.mlp.c_proj.weight", "gpt.h.19.mlp.c_proj.bias", "gpt.h.20.ln_1.weight", "gpt.h.20.ln_1.bias", "gpt.h.20.attn.bias", "gpt.h.20.attn.masked_bias", "gpt.h.20.attn.c_attn.weight", "gpt.h.20.attn.c_attn.bias", "gpt.h.20.attn.c_proj.weight", "gpt.h.20.attn.c_proj.bias", "gpt.h.20.ln_2.weight", "gpt.h.20.ln_2.bias", "gpt.h.20.mlp.c_fc.weight", "gpt.h.20.mlp.c_fc.bias", "gpt.h.20.mlp.c_proj.weight", "gpt.h.20.mlp.c_proj.bias", "gpt.h.21.ln_1.weight", "gpt.h.21.ln_1.bias", "gpt.h.21.attn.bias", "gpt.h.21.attn.masked_bias", "gpt.h.21.attn.c_attn.weight", "gpt.h.21.attn.c_attn.bias", "gpt.h.21.attn.c_proj.weight", "gpt.h.21.attn.c_proj.bias", "gpt.h.21.ln_2.weight", "gpt.h.21.ln_2.bias", "gpt.h.21.mlp.c_fc.weight", "gpt.h.21.mlp.c_fc.bias", "gpt.h.21.mlp.c_proj.weight", "gpt.h.21.mlp.c_proj.bias", "gpt.h.22.ln_1.weight", "gpt.h.22.ln_1.bias", "gpt.h.22.attn.bias", "gpt.h.22.attn.masked_bias", "gpt.h.22.attn.c_attn.weight", "gpt.h.22.attn.c_attn.bias", "gpt.h.22.attn.c_proj.weight", "gpt.h.22.attn.c_proj.bias", "gpt.h.22.ln_2.weight", "gpt.h.22.ln_2.bias", "gpt.h.22.mlp.c_fc.weight", "gpt.h.22.mlp.c_fc.bias", "gpt.h.22.mlp.c_proj.weight", "gpt.h.22.mlp.c_proj.bias", "gpt.h.23.ln_1.weight", "gpt.h.23.ln_1.bias", "gpt.h.23.attn.bias", "gpt.h.23.attn.masked_bias", "gpt.h.23.attn.c_attn.weight", "gpt.h.23.attn.c_attn.bias", "gpt.h.23.attn.c_proj.weight", "gpt.h.23.attn.c_proj.bias", "gpt.h.23.ln_2.weight", "gpt.h.23.ln_2.bias", "gpt.h.23.mlp.c_fc.weight", "gpt.h.23.mlp.c_fc.bias", "gpt.h.23.mlp.c_proj.weight", "gpt.h.23.mlp.c_proj.bias", "gpt.h.24.ln_1.weight", "gpt.h.24.ln_1.bias", "gpt.h.24.attn.bias", "gpt.h.24.attn.masked_bias", "gpt.h.24.attn.c_attn.weight", "gpt.h.24.attn.c_attn.bias", "gpt.h.24.attn.c_proj.weight", "gpt.h.24.attn.c_proj.bias", "gpt.h.24.ln_2.weight", "gpt.h.24.ln_2.bias", "gpt.h.24.mlp.c_fc.weight", "gpt.h.24.mlp.c_fc.bias", "gpt.h.24.mlp.c_proj.weight", "gpt.h.24.mlp.c_proj.bias", "gpt.h.25.ln_1.weight", "gpt.h.25.ln_1.bias", "gpt.h.25.attn.bias", "gpt.h.25.attn.masked_bias", "gpt.h.25.attn.c_attn.weight", "gpt.h.25.attn.c_attn.bias", "gpt.h.25.attn.c_proj.weight", "gpt.h.25.attn.c_proj.bias", "gpt.h.25.ln_2.weight", "gpt.h.25.ln_2.bias", "gpt.h.25.mlp.c_fc.weight", "gpt.h.25.mlp.c_fc.bias", "gpt.h.25.mlp.c_proj.weight", "gpt.h.25.mlp.c_proj.bias", "gpt.h.26.ln_1.weight", "gpt.h.26.ln_1.bias", "gpt.h.26.attn.bias", "gpt.h.26.attn.masked_bias", "gpt.h.26.attn.c_attn.weight", "gpt.h.26.attn.c_attn.bias", "gpt.h.26.attn.c_proj.weight", "gpt.h.26.attn.c_proj.bias", "gpt.h.26.ln_2.weight", "gpt.h.26.ln_2.bias", "gpt.h.26.mlp.c_fc.weight", "gpt.h.26.mlp.c_fc.bias", "gpt.h.26.mlp.c_proj.weight", "gpt.h.26.mlp.c_proj.bias", "gpt.h.27.ln_1.weight", "gpt.h.27.ln_1.bias", "gpt.h.27.attn.bias", "gpt.h.27.attn.masked_bias", "gpt.h.27.attn.c_attn.weight", "gpt.h.27.attn.c_attn.bias", "gpt.h.27.attn.c_proj.weight", "gpt.h.27.attn.c_proj.bias", "gpt.h.27.ln_2.weight", "gpt.h.27.ln_2.bias", "gpt.h.27.mlp.c_fc.weight", "gpt.h.27.mlp.c_fc.bias", "gpt.h.27.mlp.c_proj.weight", "gpt.h.27.mlp.c_proj.bias", "gpt.h.28.ln_1.weight", "gpt.h.28.ln_1.bias", "gpt.h.28.attn.bias", "gpt.h.28.attn.masked_bias", "gpt.h.28.attn.c_attn.weight", "gpt.h.28.attn.c_attn.bias", "gpt.h.28.attn.c_proj.weight", "gpt.h.28.attn.c_proj.bias", "gpt.h.28.ln_2.weight", "gpt.h.28.ln_2.bias", "gpt.h.28.mlp.c_fc.weight", "gpt.h.28.mlp.c_fc.bias", "gpt.h.28.mlp.c_proj.weight", "gpt.h.28.mlp.c_proj.bias", "gpt.h.29.ln_1.weight", "gpt.h.29.ln_1.bias", "gpt.h.29.attn.bias", "gpt.h.29.attn.masked_bias", "gpt.h.29.attn.c_attn.weight", "gpt.h.29.attn.c_attn.bias", "gpt.h.29.attn.c_proj.weight", "gpt.h.29.attn.c_proj.bias", "gpt.h.29.ln_2.weight", "gpt.h.29.ln_2.bias", "gpt.h.29.mlp.c_fc.weight", "gpt.h.29.mlp.c_fc.bias", "gpt.h.29.mlp.c_proj.weight", "gpt.h.29.mlp.c_proj.bias", "gpt.ln_f.weight", "gpt.ln_f.bias", "mel_pos_embedding.emb.weight", "text_pos_embedding.emb.weight", "final_norm.weight", "final_norm.bias", "text_head.weight", "text_head.bias", "mel_head.weight", "mel_head.bias". Unexpected key(s) in state_dict: "weight", "config", "info", "sr", "f0", "version".

It comes with a .index file which is bigger than the .pth file.
EDIT: Oh sorry, this model is for RVC. i'm an idiot. my bad.

EDIT: Oh sorry, this model is for RVC. i'm an idiot. my bad. Hi, I've got a voice model from [https://voice-models.com/model/1o4sJQdShCc](https://voice-models.com/model/1o4sJQdShCc), and when I try to load it I get a bunch of errors. `Loading autoregressive model: ./models/finetunes/PRTL2-CaveJohnson-20231018-Batch8-40kHz_e388_s19788.pth Traceback (most recent call last): File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/gradio/routes.py", line 394, in run_predict output = await app.get_blocks().process_api( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1075, in process_api result = await self.call_function( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/gradio/blocks.py", line 884, in call_function prediction = await anyio.to_thread.run_sync( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2134, in run_sync_in_worker_thread return await future File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 851, in run result = context.run(func, *args) File "/media/username/WD10BX/ai-voice-cloning/src/utils.py", line 3695, in reload_tts load_tts() File "/media/username/WD10BX/ai-voice-cloning/src/utils.py", line 3666, in load_tts tts = TorToise_TTS(minor_optimizations=not args.low_vram, autoregressive_model_path=autoregressive_model, diffusion_model_path=diffusion_model, vocoder_model=vocoder_model, tokenizer_json=tokenizer_json, unsqueeze_sample_batches=args.unsqueeze_sample_batches, use_deepspeed=args.use_deepspeed) File "/media/username/WD10BX/ai-voice-cloning/modules/tortoise-tts/tortoise/api.py", line 308, in __init__ self.load_autoregressive_model(autoregressive_model_path) File "/media/username/WD10BX/ai-voice-cloning/modules/tortoise-tts/tortoise/api.py", line 391, in load_autoregressive_model self.autoregressive.load_state_dict(torch.load(self.autoregressive_model_path)) File "/media/username/WD10BX/ai-voice-cloning/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for UnifiedVoice: Missing key(s) in state_dict: "conditioning_encoder.init.weight", "conditioning_encoder.init.bias", "conditioning_encoder.attn.0.norm.weight", "conditioning_encoder.attn.0.norm.bias", "conditioning_encoder.attn.0.qkv.weight", "conditioning_encoder.attn.0.qkv.bias", "conditioning_encoder.attn.0.proj_out.weight", "conditioning_encoder.attn.0.proj_out.bias", "conditioning_encoder.attn.1.norm.weight", "conditioning_encoder.attn.1.norm.bias", "conditioning_encoder.attn.1.qkv.weight", "conditioning_encoder.attn.1.qkv.bias", "conditioning_encoder.attn.1.proj_out.weight", "conditioning_encoder.attn.1.proj_out.bias", "conditioning_encoder.attn.2.norm.weight", "conditioning_encoder.attn.2.norm.bias", "conditioning_encoder.attn.2.qkv.weight", "conditioning_encoder.attn.2.qkv.bias", "conditioning_encoder.attn.2.proj_out.weight", "conditioning_encoder.attn.2.proj_out.bias", "conditioning_encoder.attn.3.norm.weight", "conditioning_encoder.attn.3.norm.bias", "conditioning_encoder.attn.3.qkv.weight", "conditioning_encoder.attn.3.qkv.bias", "conditioning_encoder.attn.3.proj_out.weight", "conditioning_encoder.attn.3.proj_out.bias", "conditioning_encoder.attn.4.norm.weight", "conditioning_encoder.attn.4.norm.bias", "conditioning_encoder.attn.4.qkv.weight", "conditioning_encoder.attn.4.qkv.bias", "conditioning_encoder.attn.4.proj_out.weight", "conditioning_encoder.attn.4.proj_out.bias", "conditioning_encoder.attn.5.norm.weight", "conditioning_encoder.attn.5.norm.bias", "conditioning_encoder.attn.5.qkv.weight", "conditioning_encoder.attn.5.qkv.bias", "conditioning_encoder.attn.5.proj_out.weight", "conditioning_encoder.attn.5.proj_out.bias", "text_embedding.weight", "mel_embedding.weight", "gpt.h.0.ln_1.weight", "gpt.h.0.ln_1.bias", "gpt.h.0.attn.bias", "gpt.h.0.attn.masked_bias", "gpt.h.0.attn.c_attn.weight", "gpt.h.0.attn.c_attn.bias", "gpt.h.0.attn.c_proj.weight", "gpt.h.0.attn.c_proj.bias", "gpt.h.0.ln_2.weight", "gpt.h.0.ln_2.bias", "gpt.h.0.mlp.c_fc.weight", "gpt.h.0.mlp.c_fc.bias", "gpt.h.0.mlp.c_proj.weight", "gpt.h.0.mlp.c_proj.bias", "gpt.h.1.ln_1.weight", "gpt.h.1.ln_1.bias", "gpt.h.1.attn.bias", "gpt.h.1.attn.masked_bias", "gpt.h.1.attn.c_attn.weight", "gpt.h.1.attn.c_attn.bias", "gpt.h.1.attn.c_proj.weight", "gpt.h.1.attn.c_proj.bias", "gpt.h.1.ln_2.weight", "gpt.h.1.ln_2.bias", "gpt.h.1.mlp.c_fc.weight", "gpt.h.1.mlp.c_fc.bias", "gpt.h.1.mlp.c_proj.weight", "gpt.h.1.mlp.c_proj.bias", "gpt.h.2.ln_1.weight", "gpt.h.2.ln_1.bias", "gpt.h.2.attn.bias", "gpt.h.2.attn.masked_bias", "gpt.h.2.attn.c_attn.weight", "gpt.h.2.attn.c_attn.bias", "gpt.h.2.attn.c_proj.weight", "gpt.h.2.attn.c_proj.bias", "gpt.h.2.ln_2.weight", "gpt.h.2.ln_2.bias", "gpt.h.2.mlp.c_fc.weight", "gpt.h.2.mlp.c_fc.bias", "gpt.h.2.mlp.c_proj.weight", "gpt.h.2.mlp.c_proj.bias", "gpt.h.3.ln_1.weight", "gpt.h.3.ln_1.bias", "gpt.h.3.attn.bias", "gpt.h.3.attn.masked_bias", "gpt.h.3.attn.c_attn.weight", "gpt.h.3.attn.c_attn.bias", "gpt.h.3.attn.c_proj.weight", "gpt.h.3.attn.c_proj.bias", "gpt.h.3.ln_2.weight", "gpt.h.3.ln_2.bias", "gpt.h.3.mlp.c_fc.weight", "gpt.h.3.mlp.c_fc.bias", "gpt.h.3.mlp.c_proj.weight", "gpt.h.3.mlp.c_proj.bias", "gpt.h.4.ln_1.weight", "gpt.h.4.ln_1.bias", "gpt.h.4.attn.bias", "gpt.h.4.attn.masked_bias", "gpt.h.4.attn.c_attn.weight", "gpt.h.4.attn.c_attn.bias", "gpt.h.4.attn.c_proj.weight", "gpt.h.4.attn.c_proj.bias", "gpt.h.4.ln_2.weight", "gpt.h.4.ln_2.bias", "gpt.h.4.mlp.c_fc.weight", "gpt.h.4.mlp.c_fc.bias", "gpt.h.4.mlp.c_proj.weight", "gpt.h.4.mlp.c_proj.bias", "gpt.h.5.ln_1.weight", "gpt.h.5.ln_1.bias", "gpt.h.5.attn.bias", "gpt.h.5.attn.masked_bias", "gpt.h.5.attn.c_attn.weight", "gpt.h.5.attn.c_attn.bias", "gpt.h.5.attn.c_proj.weight", "gpt.h.5.attn.c_proj.bias", "gpt.h.5.ln_2.weight", "gpt.h.5.ln_2.bias", "gpt.h.5.mlp.c_fc.weight", "gpt.h.5.mlp.c_fc.bias", "gpt.h.5.mlp.c_proj.weight", "gpt.h.5.mlp.c_proj.bias", "gpt.h.6.ln_1.weight", "gpt.h.6.ln_1.bias", "gpt.h.6.attn.bias", "gpt.h.6.attn.masked_bias", "gpt.h.6.attn.c_attn.weight", "gpt.h.6.attn.c_attn.bias", "gpt.h.6.attn.c_proj.weight", "gpt.h.6.attn.c_proj.bias", "gpt.h.6.ln_2.weight", "gpt.h.6.ln_2.bias", "gpt.h.6.mlp.c_fc.weight", "gpt.h.6.mlp.c_fc.bias", "gpt.h.6.mlp.c_proj.weight", "gpt.h.6.mlp.c_proj.bias", "gpt.h.7.ln_1.weight", "gpt.h.7.ln_1.bias", "gpt.h.7.attn.bias", "gpt.h.7.attn.masked_bias", "gpt.h.7.attn.c_attn.weight", "gpt.h.7.attn.c_attn.bias", "gpt.h.7.attn.c_proj.weight", "gpt.h.7.attn.c_proj.bias", "gpt.h.7.ln_2.weight", "gpt.h.7.ln_2.bias", "gpt.h.7.mlp.c_fc.weight", "gpt.h.7.mlp.c_fc.bias", "gpt.h.7.mlp.c_proj.weight", "gpt.h.7.mlp.c_proj.bias", "gpt.h.8.ln_1.weight", "gpt.h.8.ln_1.bias", "gpt.h.8.attn.bias", "gpt.h.8.attn.masked_bias", "gpt.h.8.attn.c_attn.weight", "gpt.h.8.attn.c_attn.bias", "gpt.h.8.attn.c_proj.weight", "gpt.h.8.attn.c_proj.bias", "gpt.h.8.ln_2.weight", "gpt.h.8.ln_2.bias", "gpt.h.8.mlp.c_fc.weight", "gpt.h.8.mlp.c_fc.bias", "gpt.h.8.mlp.c_proj.weight", "gpt.h.8.mlp.c_proj.bias", "gpt.h.9.ln_1.weight", "gpt.h.9.ln_1.bias", "gpt.h.9.attn.bias", "gpt.h.9.attn.masked_bias", "gpt.h.9.attn.c_attn.weight", "gpt.h.9.attn.c_attn.bias", "gpt.h.9.attn.c_proj.weight", "gpt.h.9.attn.c_proj.bias", "gpt.h.9.ln_2.weight", "gpt.h.9.ln_2.bias", "gpt.h.9.mlp.c_fc.weight", "gpt.h.9.mlp.c_fc.bias", "gpt.h.9.mlp.c_proj.weight", "gpt.h.9.mlp.c_proj.bias", "gpt.h.10.ln_1.weight", "gpt.h.10.ln_1.bias", "gpt.h.10.attn.bias", "gpt.h.10.attn.masked_bias", "gpt.h.10.attn.c_attn.weight", "gpt.h.10.attn.c_attn.bias", "gpt.h.10.attn.c_proj.weight", "gpt.h.10.attn.c_proj.bias", "gpt.h.10.ln_2.weight", "gpt.h.10.ln_2.bias", "gpt.h.10.mlp.c_fc.weight", "gpt.h.10.mlp.c_fc.bias", "gpt.h.10.mlp.c_proj.weight", "gpt.h.10.mlp.c_proj.bias", "gpt.h.11.ln_1.weight", "gpt.h.11.ln_1.bias", "gpt.h.11.attn.bias", "gpt.h.11.attn.masked_bias", "gpt.h.11.attn.c_attn.weight", "gpt.h.11.attn.c_attn.bias", "gpt.h.11.attn.c_proj.weight", "gpt.h.11.attn.c_proj.bias", "gpt.h.11.ln_2.weight", "gpt.h.11.ln_2.bias", "gpt.h.11.mlp.c_fc.weight", "gpt.h.11.mlp.c_fc.bias", "gpt.h.11.mlp.c_proj.weight", "gpt.h.11.mlp.c_proj.bias", "gpt.h.12.ln_1.weight", "gpt.h.12.ln_1.bias", "gpt.h.12.attn.bias", "gpt.h.12.attn.masked_bias", "gpt.h.12.attn.c_attn.weight", "gpt.h.12.attn.c_attn.bias", "gpt.h.12.attn.c_proj.weight", "gpt.h.12.attn.c_proj.bias", "gpt.h.12.ln_2.weight", "gpt.h.12.ln_2.bias", "gpt.h.12.mlp.c_fc.weight", "gpt.h.12.mlp.c_fc.bias", "gpt.h.12.mlp.c_proj.weight", "gpt.h.12.mlp.c_proj.bias", "gpt.h.13.ln_1.weight", "gpt.h.13.ln_1.bias", "gpt.h.13.attn.bias", "gpt.h.13.attn.masked_bias", "gpt.h.13.attn.c_attn.weight", "gpt.h.13.attn.c_attn.bias", "gpt.h.13.attn.c_proj.weight", "gpt.h.13.attn.c_proj.bias", "gpt.h.13.ln_2.weight", "gpt.h.13.ln_2.bias", "gpt.h.13.mlp.c_fc.weight", "gpt.h.13.mlp.c_fc.bias", "gpt.h.13.mlp.c_proj.weight", "gpt.h.13.mlp.c_proj.bias", "gpt.h.14.ln_1.weight", "gpt.h.14.ln_1.bias", "gpt.h.14.attn.bias", "gpt.h.14.attn.masked_bias", "gpt.h.14.attn.c_attn.weight", "gpt.h.14.attn.c_attn.bias", "gpt.h.14.attn.c_proj.weight", "gpt.h.14.attn.c_proj.bias", "gpt.h.14.ln_2.weight", "gpt.h.14.ln_2.bias", "gpt.h.14.mlp.c_fc.weight", "gpt.h.14.mlp.c_fc.bias", "gpt.h.14.mlp.c_proj.weight", "gpt.h.14.mlp.c_proj.bias", "gpt.h.15.ln_1.weight", "gpt.h.15.ln_1.bias", "gpt.h.15.attn.bias", "gpt.h.15.attn.masked_bias", "gpt.h.15.attn.c_attn.weight", "gpt.h.15.attn.c_attn.bias", "gpt.h.15.attn.c_proj.weight", "gpt.h.15.attn.c_proj.bias", "gpt.h.15.ln_2.weight", "gpt.h.15.ln_2.bias", "gpt.h.15.mlp.c_fc.weight", "gpt.h.15.mlp.c_fc.bias", "gpt.h.15.mlp.c_proj.weight", "gpt.h.15.mlp.c_proj.bias", "gpt.h.16.ln_1.weight", "gpt.h.16.ln_1.bias", "gpt.h.16.attn.bias", "gpt.h.16.attn.masked_bias", "gpt.h.16.attn.c_attn.weight", "gpt.h.16.attn.c_attn.bias", "gpt.h.16.attn.c_proj.weight", "gpt.h.16.attn.c_proj.bias", "gpt.h.16.ln_2.weight", "gpt.h.16.ln_2.bias", "gpt.h.16.mlp.c_fc.weight", "gpt.h.16.mlp.c_fc.bias", "gpt.h.16.mlp.c_proj.weight", "gpt.h.16.mlp.c_proj.bias", "gpt.h.17.ln_1.weight", "gpt.h.17.ln_1.bias", "gpt.h.17.attn.bias", "gpt.h.17.attn.masked_bias", "gpt.h.17.attn.c_attn.weight", "gpt.h.17.attn.c_attn.bias", "gpt.h.17.attn.c_proj.weight", "gpt.h.17.attn.c_proj.bias", "gpt.h.17.ln_2.weight", "gpt.h.17.ln_2.bias", "gpt.h.17.mlp.c_fc.weight", "gpt.h.17.mlp.c_fc.bias", "gpt.h.17.mlp.c_proj.weight", "gpt.h.17.mlp.c_proj.bias", "gpt.h.18.ln_1.weight", "gpt.h.18.ln_1.bias", "gpt.h.18.attn.bias", "gpt.h.18.attn.masked_bias", "gpt.h.18.attn.c_attn.weight", "gpt.h.18.attn.c_attn.bias", "gpt.h.18.attn.c_proj.weight", "gpt.h.18.attn.c_proj.bias", "gpt.h.18.ln_2.weight", "gpt.h.18.ln_2.bias", "gpt.h.18.mlp.c_fc.weight", "gpt.h.18.mlp.c_fc.bias", "gpt.h.18.mlp.c_proj.weight", "gpt.h.18.mlp.c_proj.bias", "gpt.h.19.ln_1.weight", "gpt.h.19.ln_1.bias", "gpt.h.19.attn.bias", "gpt.h.19.attn.masked_bias", "gpt.h.19.attn.c_attn.weight", "gpt.h.19.attn.c_attn.bias", "gpt.h.19.attn.c_proj.weight", "gpt.h.19.attn.c_proj.bias", "gpt.h.19.ln_2.weight", "gpt.h.19.ln_2.bias", "gpt.h.19.mlp.c_fc.weight", "gpt.h.19.mlp.c_fc.bias", "gpt.h.19.mlp.c_proj.weight", "gpt.h.19.mlp.c_proj.bias", "gpt.h.20.ln_1.weight", "gpt.h.20.ln_1.bias", "gpt.h.20.attn.bias", "gpt.h.20.attn.masked_bias", "gpt.h.20.attn.c_attn.weight", "gpt.h.20.attn.c_attn.bias", "gpt.h.20.attn.c_proj.weight", "gpt.h.20.attn.c_proj.bias", "gpt.h.20.ln_2.weight", "gpt.h.20.ln_2.bias", "gpt.h.20.mlp.c_fc.weight", "gpt.h.20.mlp.c_fc.bias", "gpt.h.20.mlp.c_proj.weight", "gpt.h.20.mlp.c_proj.bias", "gpt.h.21.ln_1.weight", "gpt.h.21.ln_1.bias", "gpt.h.21.attn.bias", "gpt.h.21.attn.masked_bias", "gpt.h.21.attn.c_attn.weight", "gpt.h.21.attn.c_attn.bias", "gpt.h.21.attn.c_proj.weight", "gpt.h.21.attn.c_proj.bias", "gpt.h.21.ln_2.weight", "gpt.h.21.ln_2.bias", "gpt.h.21.mlp.c_fc.weight", "gpt.h.21.mlp.c_fc.bias", "gpt.h.21.mlp.c_proj.weight", "gpt.h.21.mlp.c_proj.bias", "gpt.h.22.ln_1.weight", "gpt.h.22.ln_1.bias", "gpt.h.22.attn.bias", "gpt.h.22.attn.masked_bias", "gpt.h.22.attn.c_attn.weight", "gpt.h.22.attn.c_attn.bias", "gpt.h.22.attn.c_proj.weight", "gpt.h.22.attn.c_proj.bias", "gpt.h.22.ln_2.weight", "gpt.h.22.ln_2.bias", "gpt.h.22.mlp.c_fc.weight", "gpt.h.22.mlp.c_fc.bias", "gpt.h.22.mlp.c_proj.weight", "gpt.h.22.mlp.c_proj.bias", "gpt.h.23.ln_1.weight", "gpt.h.23.ln_1.bias", "gpt.h.23.attn.bias", "gpt.h.23.attn.masked_bias", "gpt.h.23.attn.c_attn.weight", "gpt.h.23.attn.c_attn.bias", "gpt.h.23.attn.c_proj.weight", "gpt.h.23.attn.c_proj.bias", "gpt.h.23.ln_2.weight", "gpt.h.23.ln_2.bias", "gpt.h.23.mlp.c_fc.weight", "gpt.h.23.mlp.c_fc.bias", "gpt.h.23.mlp.c_proj.weight", "gpt.h.23.mlp.c_proj.bias", "gpt.h.24.ln_1.weight", "gpt.h.24.ln_1.bias", "gpt.h.24.attn.bias", "gpt.h.24.attn.masked_bias", "gpt.h.24.attn.c_attn.weight", "gpt.h.24.attn.c_attn.bias", "gpt.h.24.attn.c_proj.weight", "gpt.h.24.attn.c_proj.bias", "gpt.h.24.ln_2.weight", "gpt.h.24.ln_2.bias", "gpt.h.24.mlp.c_fc.weight", "gpt.h.24.mlp.c_fc.bias", "gpt.h.24.mlp.c_proj.weight", "gpt.h.24.mlp.c_proj.bias", "gpt.h.25.ln_1.weight", "gpt.h.25.ln_1.bias", "gpt.h.25.attn.bias", "gpt.h.25.attn.masked_bias", "gpt.h.25.attn.c_attn.weight", "gpt.h.25.attn.c_attn.bias", "gpt.h.25.attn.c_proj.weight", "gpt.h.25.attn.c_proj.bias", "gpt.h.25.ln_2.weight", "gpt.h.25.ln_2.bias", "gpt.h.25.mlp.c_fc.weight", "gpt.h.25.mlp.c_fc.bias", "gpt.h.25.mlp.c_proj.weight", "gpt.h.25.mlp.c_proj.bias", "gpt.h.26.ln_1.weight", "gpt.h.26.ln_1.bias", "gpt.h.26.attn.bias", "gpt.h.26.attn.masked_bias", "gpt.h.26.attn.c_attn.weight", "gpt.h.26.attn.c_attn.bias", "gpt.h.26.attn.c_proj.weight", "gpt.h.26.attn.c_proj.bias", "gpt.h.26.ln_2.weight", "gpt.h.26.ln_2.bias", "gpt.h.26.mlp.c_fc.weight", "gpt.h.26.mlp.c_fc.bias", "gpt.h.26.mlp.c_proj.weight", "gpt.h.26.mlp.c_proj.bias", "gpt.h.27.ln_1.weight", "gpt.h.27.ln_1.bias", "gpt.h.27.attn.bias", "gpt.h.27.attn.masked_bias", "gpt.h.27.attn.c_attn.weight", "gpt.h.27.attn.c_attn.bias", "gpt.h.27.attn.c_proj.weight", "gpt.h.27.attn.c_proj.bias", "gpt.h.27.ln_2.weight", "gpt.h.27.ln_2.bias", "gpt.h.27.mlp.c_fc.weight", "gpt.h.27.mlp.c_fc.bias", "gpt.h.27.mlp.c_proj.weight", "gpt.h.27.mlp.c_proj.bias", "gpt.h.28.ln_1.weight", "gpt.h.28.ln_1.bias", "gpt.h.28.attn.bias", "gpt.h.28.attn.masked_bias", "gpt.h.28.attn.c_attn.weight", "gpt.h.28.attn.c_attn.bias", "gpt.h.28.attn.c_proj.weight", "gpt.h.28.attn.c_proj.bias", "gpt.h.28.ln_2.weight", "gpt.h.28.ln_2.bias", "gpt.h.28.mlp.c_fc.weight", "gpt.h.28.mlp.c_fc.bias", "gpt.h.28.mlp.c_proj.weight", "gpt.h.28.mlp.c_proj.bias", "gpt.h.29.ln_1.weight", "gpt.h.29.ln_1.bias", "gpt.h.29.attn.bias", "gpt.h.29.attn.masked_bias", "gpt.h.29.attn.c_attn.weight", "gpt.h.29.attn.c_attn.bias", "gpt.h.29.attn.c_proj.weight", "gpt.h.29.attn.c_proj.bias", "gpt.h.29.ln_2.weight", "gpt.h.29.ln_2.bias", "gpt.h.29.mlp.c_fc.weight", "gpt.h.29.mlp.c_fc.bias", "gpt.h.29.mlp.c_proj.weight", "gpt.h.29.mlp.c_proj.bias", "gpt.ln_f.weight", "gpt.ln_f.bias", "mel_pos_embedding.emb.weight", "text_pos_embedding.emb.weight", "final_norm.weight", "final_norm.bias", "text_head.weight", "text_head.bias", "mel_head.weight", "mel_head.bias". Unexpected key(s) in state_dict: "weight", "config", "info", "sr", "f0", "version". ` It comes with a .index file which is bigger than the .pth file. EDIT: Oh sorry, this model is for RVC. i'm an idiot. my bad.

Screenshot from 2024-01-25 16-14-50.png

18 KiB