Skip to content

SOTA Open Source TTS

"Ensure the version of checkpoints" (#752)

PoTaTof54c50fe6239
diff --git a/API_FLAGS.txt b/API_FLAGS.txt
index 4a49f14..96a6bee 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 8cd7834..9c716fe 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 e5d2e80..daae046 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 f597983..216890d 100644
--- a/tools/llama/generate.py
+++ b/tools/llama/generate.py
@@ -1019,7 +1019,7 @@ def launch_thread_safe_queue_agent(
@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 11e8e14..7b2be2e 100644
--- a/tools/vqgan/extract_vq.py
+++ b/tools/vqgan/extract_vq.py
@@ -48,7 +48,7 @@ logger.add(sys.stderr, format=logger_format)
@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 8c69d99..2a63165 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",