FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/fish-speech-1.4/tokenizer.tiktoken'

[digital-era]

Self Checks

• [X] This template is only for bug reports. For questions, please visit Discussions.
• [X] I have thoroughly reviewed the project documentation (installation, training, inference) but couldn't find information to solve my problem. English 中文 日本語 Portuguese (Brazil)
• [X] I have searched for existing issues, including closed ones. Search issues
• [X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [X] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• [X] Please do not modify this template and fill in all required fields.

Cloud or Self Hosted

Cloud

Environment Details

Google Colab python 3.10

Steps to Reproduce

!python tools/vqgan/inference.py -i {src_A_audio} --checkpoint-path "checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth" --output-path {reference_A_audio} --device cpu #cuda

!python tools/llama/generate.py --text {target_text} --prompt-text "The text corresponding to reference audio" --prompt-tokens {reference_A_token} --checkpoint-path "checkpoints/fish-speech-1.4" --num-samples 2 --device cpu #cuda

✔️ Expected Behavior

Run thgrouth and generat codes_0.npy

❌ Actual Behavior

Traceback (most recent call last): File "/content/fish-speech/tools/llama/generate.py", line 1115, in main() File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1157, in call return self.main(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1078, in main rv = self.invoke(ctx) File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1434, in invoke return ctx.invoke(self.callback, **ctx.params) File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 783, in invoke return __callback(*args, **kwargs) File "/content/fish-speech/tools/llama/generate.py", line 1057, in main model, decode_one_token = load_model( File "/content/fish-speech/tools/llama/generate.py", line 677, in load_model model: Union[NaiveTransformer, DualARTransformer] = BaseTransformer.from_pretrained( File "/content/fish-speech/fish_speech/models/text2semantic/llama.py", line 408, in from_pretrained tokenizer = FishTokenizer(tokenizer_path) File "/content/fish-speech/fish_speech/tokenizer.py", line 67, in init mergeable_ranks = self.load_tiktoken_bpe(model_path) File "/content/fish-speech/fish_speech/tokenizer.py", line 89, in load_tiktoken_bpe for line in open(tiktoken_bpe_file).read().splitlines(): FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/fish-speech-1.4/tokenizer.tiktoken' Usage: inference.py [OPTIONS] Try 'inference.py --help' for help.