#Not working with MacOs Sonoma

63 messages · Page 1 of 1 (latest)

acoustic maple
#

Since the update, the voice sound terrible. Confirmed by other users on AI Hub.

drifting compass
marsh basin
#

Both, it's primarily an issue with the mps backend

elfin stratus
#

it's already solved

elfin stratus
old ocean
#

how to solve?

#

I also meet the same question

#

the voice sound terrible with MacOs Sonoma

#

@elfin stratus

elfin stratus
#

inferences or training

old ocean
#

inferences

#

It sounds terrible

elfin stratus
#

I can hear it

old ocean
elfin stratus
#

is imput

old ocean
#

2 months ago is ok

elfin stratus
#

explain better

old ocean
#

It sounds good when I used RVC 2 months ago

elfin stratus
#

I think it's in imput

old ocean
#

how to solve

#

I try many audio

#

they all sound terrible

elfin stratus
#

look at your terminal

#

send me what it says

old ocean
#

Running on local URL: http://0.0.0.0:7865
loading weights/Elvis50v2.pth
gin_channels: 256 self.spk_embed_dim: 109
<All keys matched successfully>
2023-11-04 15:08:13 | INFO | fairseq.tasks.hubert_pretraining | current directory is /Users/wendao/RVC
2023-11-04 15:08:13 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False}
2023-11-04 15:08:13 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False}

#

@elfin stratus

elfin stratus
#

it doesn't give any error

#

change it to mangio or others

#

use it in mangio crepe and see how it looks in audio

old ocean
#

what's the mangio crepe?

elfin stratus
#

send a photo of the interface

old ocean
#

It sounds....

#

I use this RVC version

elfin stratus
old ocean
#

I changed to Mangio Crepé RVC2

#

It's the Macos Sonoma's issue

elfin stratus
#

let me read that

worn tulip
#

I have the same issue. Someone with MacOs Sonoma that have a solution for this?

elfin stratus
#

put this on your terminal

#

hit enter

worn tulip
#

I already done that on sonoma 14.0 but it did not worked
It will work on Sonoma 14.1?

worn tulip
elfin stratus
worn tulip
#

tested also with the Sonoma. I will try the Mangio Crepé RVC2

elfin stratus
worn tulip
#

didn't works. Just a terrible output also with the RVC2

worn tulip
#

@old ocean did you figure out how to solve this?

old ocean
#

pip3 uninstall torch

#

pip3 install torch=2.1.0

worn tulip
#

still the same

worn tulip
# old ocean pip3 uninstall torch

well after that it started working with old trained models generated before the upgrade to Sonoma. With new trained models the inferences are just moaning sounds

elfin stratus