#!/usr/bin/env python
# coding: utf-8

# # Fish Speech

# ### For Windows User / win用户

# In[ ]:


get_ipython().system('chcp 65001')


# ### For Linux User / Linux 用户

# In[ ]:


import locale
locale.setlocale(locale.LC_ALL, 'en_US.UTF-8')


# ### Prepare Model

# In[ ]:


# For Chinese users, you probably want to use mirror to accelerate downloading
# !set HF_ENDPOINT=https://hf-mirror.com
# !export HF_ENDPOINT=https://hf-mirror.com 

get_ipython().system('huggingface-cli download fishaudio/fish-speech-1.4 --local-dir checkpoints/fish-speech-1.4/')


# ## WebUI Inference
# 
# > You can use --compile to fuse CUDA kernels for faster inference (10x).

# In[ ]:


get_ipython().system('python tools/webui.py      --llama-checkpoint-path checkpoints/fish-speech-1.4      --decoder-checkpoint-path checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth      # --compile')


# ## Break-down CLI Inference

# ### 1. Encode reference audio: / 从语音生成 prompt: 
# 
# You should get a `fake.npy` file.
# 
# 你应该能得到一个 `fake.npy` 文件.

# In[ ]:


## Enter the path to the audio file here
src_audio = r"D:\PythonProject\vo_hutao_draw_appear.wav"

get_ipython().system('python tools/vqgan/inference.py      -i {src_audio}      --checkpoint-path "checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth"')

from IPython.display import Audio, display
audio = Audio(filename="fake.wav")
display(audio)


# ### 2. Generate semantic tokens from text: / 从文本生成语义 token:
# 
# > This command will create a codes_N file in the working directory, where N is an integer starting from 0.
# 
# > You may want to use `--compile` to fuse CUDA kernels for faster inference (~30 tokens/second -> ~300 tokens/second).
# 
# > 该命令会在工作目录下创建 codes_N 文件, 其中 N 是从 0 开始的整数.
# 
# > 您可以使用 `--compile` 来融合 cuda 内核以实现更快的推理 (~30 tokens/秒 -> ~300 tokens/秒)

# In[ ]:


get_ipython().system('python tools/llama/generate.py      --text "hello world"      --prompt-text "The text corresponding to reference audio"      --prompt-tokens "fake.npy"      --checkpoint-path "checkpoints/fish-speech-1.4"      --num-samples 2')
    # --compile


# ### 3. Generate speech from semantic tokens: / 从语义 token 生成人声:

# In[ ]:


get_ipython().system('python tools/vqgan/inference.py      -i "codes_0.npy"      --checkpoint-path "checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth"')

from IPython.display import Audio, display
audio = Audio(filename="fake.wav")
display(audio)