FunAudioLLM/CosyVoice-300M

Greetings, thanks for sharing this amazing work!
Currently encountering the following error outputted during the build:
runtime error
_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml config_name=multilingual rank_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/multilingual.tiktoken
load tokenizer failed
break model index not valid
failed to do test: failed to open file: /home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml
INFO:root:input frame rate=50
load leagacy transf breakmodel
load leagacy transf breakmodel
festival_initialize() called more than once
open voice lang map failed
set used by tts frd
failed to do test: failed to open file: /home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml
Create TikTokenTokenizer with config_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml config_name=multilingual rank_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/multilingual.tiktoken
load tokenizer failed
break model index not valid
INFO:httpx:HTTP Request: POST http://device-api.zero/startup-report "HTTP/1.1 500 Internal Server Error"
Traceback (most recent call last):
  File "/home/user/app/app.py", line 92, in <module>
    preset()
  File "/home/user/app/css/preset.py", line 18, in preset
    def generate_audio(_sound_radio, _synthetic_input_textbox, _seed):
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 75, in GPU
    return _GPU(task, duration)
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 107, in _GPU
    client.startup_report()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 45, in startup_report
    raise RuntimeError("Error while initializing ZeroGPU: Unknown")
RuntimeError: Error while initializing ZeroGPU: Unknown
INFO:httpx:HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
INFO:httpx:HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
Container logs:

===== Application Startup at 2024-08-05 01:45:48 =====

INFO:httpx:HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK"
2024-08-05 03:47:42,447 - modelscope - INFO - PyTorch version 2.3.1 Found.
2024-08-05 03:47:42,448 - modelscope - INFO - Loading ast index from /home/user/.cache/modelscope/ast_indexer
2024-08-05 03:47:42,448 - modelscope - INFO - No valid ast index found from /home/user/.cache/modelscope/ast_indexer, generating ast index from prebuilt!
2024-08-05 03:47:42,578 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 e91a514c45ce34db24ea22ebbd1c0d08 and a total number of 980 components indexed
transformer is not installed, please install it if you want to use related modules
2024-08-05 03:47:43,700 - modelscope - WARNING - Using the master branch is fragile, please use it with caution!
2024-08-05 03:47:43,701 - modelscope - INFO - Use user-specified model revision: master


Downloading:   0%|          | 0.00/3.82M [00:00<?, ?B/s]

Downloading:  26%|██▌       | 1.00M/3.82M [00:01<00:04, 672kB/s]
Downloading: 100%|██████████| 3.82M/3.82M [00:01<00:00, 2.29MB/s]
2024-08-05 03:47:46,901 - modelscope - WARNING - Using the master branch is fragile, please use it with caution!
2024-08-05 03:47:46,902 - modelscope - INFO - Use user-specified model revision: master


Downloading:   0%|          | 0.00/1.09M [00:00<?, ?B/s]

Downloading:  92%|█████████▏| 1.00M/1.09M [00:01<00:00, 689kB/s]
Downloading: 100%|██████████| 1.09M/1.09M [00:01<00:00, 752kB/s]
Processing ./ttsfrd_dependency-0.1-py3-none-any.whl
Installing collected packages: ttsfrd-dependency
Successfully installed ttsfrd-dependency-0.1

[notice] A new release of pip available: 22.3.1 -> 24.2
[notice] To update, run: pip install --upgrade pip
Processing ./ttsfrd-0.3.9-cp310-cp310-linux_x86_64.whl
Installing collected packages: ttsfrd
Successfully installed ttsfrd-0.3.9

[notice] A new release of pip available: 22.3.1 -> 24.2
[notice] To update, run: pip install --upgrade pip
/usr/local/lib/python3.10/site-packages/torch/_jit_internal.py:739: FutureWarning: ignore(True) has been deprecated. TorchScript will now drop the function call on compilation. Use torch.jit.unused now. {}
  warnings.warn(
/usr/local/lib/python3.10/site-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.
  deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
INFO:root:input frame rate=50
/usr/local/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
  warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
/home/user/app/cosyvoice/dataset/processor.py:24: UserWarning: torchaudio._backend.set_audio_backend has been deprecated. With dispatcher enabled, this function is no-op. You can remove the function call.
  torchaudio.set_audio_backend('soundfile')
load leagacy transf breakmodel
load leagacy transf breakmodel
text.cc: festival_Text_init
open voice lang map failed
set used by tts frd
Create TikTokenTokenizer with config_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml config_name=multilingual rank_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/multilingual.tiktoken
load tokenizer failed
break model index not valid
failed to do test: failed to open file: /home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml
/usr/local/lib/python3.10/site-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`.
  deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message)
INFO:root:input frame rate=50
load leagacy transf breakmodel
load leagacy transf breakmodel
festival_initialize() called more than once
open voice lang map failed
set used by tts frd
Create TikTokenTokenizer with config_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml config_name=multilingual rank_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/multilingual.tiktoken
load tokenizer failed
break model index not valid
failed to do test: failed to open file: /home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml
INFO:root:input frame rate=50
load leagacy transf breakmodel
load leagacy transf breakmodel
festival_initialize() called more than once
open voice lang map failed
set used by tts frd
failed to do test: failed to open file: /home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml
Create TikTokenTokenizer with config_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/tiktoken.toml config_name=multilingual rank_path=/home/user/app/cosyvoice/cli/../../pretrained_models/speech_kantts_ttsfrd/resource/tokenizer/multilingual.tiktoken
load tokenizer failed
break model index not valid
INFO:httpx:HTTP Request: POST http://device-api.zero/startup-report "HTTP/1.1 500 Internal Server Error"
Traceback (most recent call last):
  File "/home/user/app/app.py", line 92, in <module>
    preset()
  File "/home/user/app/css/preset.py", line 18, in preset
    def generate_audio(_sound_radio, _synthetic_input_textbox, _seed):
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 75, in GPU
    return _GPU(task, duration)
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/decorator.py", line 107, in _GPU
    client.startup_report()
  File "/usr/local/lib/python3.10/site-packages/spaces/zero/client.py", line 45, in startup_report
    raise RuntimeError("Error while initializing ZeroGPU: Unknown")
RuntimeError: Error while initializing ZeroGPU: Unknown
INFO:httpx:HTTP Request: GET https://checkip.amazonaws.com/ "HTTP/1.1 200 "
INFO:httpx:HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK"
2024-08-05 03:50:40,529 - modelscope - INFO - PyTorch version 2.3.1 Found.
2024-08-05 03:50:40,531 - modelscope - INFO - Loading ast index from /home/user/.cache/modelscope/ast_indexer
2024-08-05 03:50:40,531 - modelscope - INFO - No valid ast index found from /home/user/.cache/modelscope/ast_indexer, generating ast index from prebuilt!
2024-08-05 03:50:40,663 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 e91a514c45ce34db24ea22ebbd1c0d08 and a total number of 980 components indexed
transformer is not installed, please install it if you want to use related modules
2024-08-05 03:50:41,957 - modelscope - WARNING - Using the master branch is fragile, please use it with caution!
2024-08-05 03:50:41,957 - modelscope - INFO - Use user-specified model revision: master
Spaces:

FunAudioLLM
/

CosyVoice-300M

Running on Zero

Space failing
