From f54c50fe6239d252be88a72433580fdb4118d350 Mon Sep 17 00:00:00 2001
From: PoTaTo <148920650+PoTaTo-Mika@users.noreply.github.com>
Date: Sun, 15 Dec 2024 12:46:17 +0800
Subject: [PATCH] "Ensure the version of checkpoints" (#752)

---
 API_FLAGS.txt             | 4 ++--
 dockerfile                | 2 +-
 docs/pt/inference.md      | 2 +-
 tools/llama/generate.py   | 2 +-
 tools/vqgan/extract_vq.py | 4 ++--
 tools/vqgan/inference.py  | 2 +-
 6 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/API_FLAGS.txt b/API_FLAGS.txt
index 4a49f141..96a6beea 100644
--- a/API_FLAGS.txt
+++ b/API_FLAGS.txt
@@ -1,6 +1,6 @@
 # --infer
 --api
 --listen 0.0.0.0:8080 \
---llama-checkpoint-path "checkpoints/fish-speech-1.4" \
---decoder-checkpoint-path "checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth" \
+--llama-checkpoint-path "checkpoints/fish-speech-1.5" \
+--decoder-checkpoint-path "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth" \
 --decoder-config-name firefly_gan_vq
diff --git a/dockerfile b/dockerfile
index 8cd7834e..9c716fe5 100644
--- a/dockerfile
+++ b/dockerfile
@@ -1,7 +1,7 @@
 FROM python:3.12-slim-bookworm AS stage-1
 ARG TARGETARCH
 
-ARG HUGGINGFACE_MODEL=fish-speech-1.4
+ARG HUGGINGFACE_MODEL=fish-speech-1.5
 ARG HF_ENDPOINT=https://huggingface.co
 
 WORKDIR /opt/fish-speech
diff --git a/docs/pt/inference.md b/docs/pt/inference.md
index e5d2e802..daae046d 100644
--- a/docs/pt/inference.md
+++ b/docs/pt/inference.md
@@ -70,7 +70,7 @@ Fornecemos uma API HTTP para inferência. O seguinte comando pode ser usado para
 python -m tools.api_server \
     --listen 0.0.0.0:8080 \
     --llama-checkpoint-path "checkpoints/fish-speech-1.5" \
-    --decoder-checkpoint-path "checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth" \
+    --decoder-checkpoint-path "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth" \
     --decoder-config-name firefly_gan_vq
 ```
 
diff --git a/tools/llama/generate.py b/tools/llama/generate.py
index f5979831..216890dc 100644
--- a/tools/llama/generate.py
+++ b/tools/llama/generate.py
@@ -1019,7 +1019,7 @@ def worker():
 @click.option(
     "--checkpoint-path",
     type=click.Path(path_type=Path, exists=True),
-    default="checkpoints/fish-speech-1.4",
+    default="checkpoints/fish-speech-1.5",
 )
 @click.option("--device", type=str, default="cuda")
 @click.option("--compile/--no-compile", default=False)
diff --git a/tools/vqgan/extract_vq.py b/tools/vqgan/extract_vq.py
index 11e8e143..7b2be2e6 100644
--- a/tools/vqgan/extract_vq.py
+++ b/tools/vqgan/extract_vq.py
@@ -48,7 +48,7 @@
 @lru_cache(maxsize=1)
 def get_model(
     config_name: str = "firefly_gan_vq",
-    checkpoint_path: str = "checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth",
+    checkpoint_path: str = "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth",
     device: str | torch.device = "cuda",
 ):
     with initialize(version_base="1.3", config_path="../../fish_speech/configs"):
@@ -139,7 +139,7 @@ def process_batch(files: list[Path], model) -> float:
 @click.option("--config-name", default="firefly_gan_vq")
 @click.option(
     "--checkpoint-path",
-    default="checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth",
+    default="checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth",
 )
 @click.option("--batch-size", default=64)
 @click.option("--filelist", default=None, type=Path)
diff --git a/tools/vqgan/inference.py b/tools/vqgan/inference.py
index 8c69d99d..2a631650 100644
--- a/tools/vqgan/inference.py
+++ b/tools/vqgan/inference.py
@@ -58,7 +58,7 @@ def load_model(config_name, checkpoint_path, device="cuda"):
 @click.option("--config-name", default="firefly_gan_vq")
 @click.option(
     "--checkpoint-path",
-    default="checkpoints/fish-speech-1.4/firefly-gan-vq-fsq-8x1024-21hz-generator.pth",
+    default="checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth",
 )
 @click.option(
     "--device",