[TTS][New Model] support bosonai/higgs-audio-v3-tts-4b (#4169)
Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com> Signed-off-by: Yueqian Lin <linyueqian@outlook.com> Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
This commit is contained in:
1 parent
963ba1ab7a
commit
82e74ce972
22 files changed
+4295
No files matched your search
@@ -0,0 +1,40 @@
|
||||
# Higgs-Audio V3 Online Serving
|
||||
|
||||
## Start the server
|
||||
|
||||
```bash
|
||||
# Default: GPU 0, port 8095
|
||||
./examples/online_serving/text_to_speech/higgs_audio_v3/run_server.sh
|
||||
|
||||
# Custom GPU / port
|
||||
PORT=8096 GPUS=0,1 ./examples/online_serving/text_to_speech/higgs_audio_v3/run_server.sh
|
||||
```
|
||||
|
||||
## Plain text TTS
|
||||
|
||||
```bash
|
||||
python examples/online_serving/text_to_speech/higgs_audio_v3/batch_speech_client.py \
|
||||
--base-url http://localhost:8095 \
|
||||
--output-dir /tmp/higgs_v3_batch \
|
||||
--prompts "Hello world." "The quick brown fox jumps over the lazy dog."
|
||||
```
|
||||
|
||||
## Voice clone
|
||||
|
||||
```bash
|
||||
python examples/online_serving/text_to_speech/higgs_audio_v3/batch_speech_client.py \
|
||||
--base-url http://localhost:8095 \
|
||||
--output-dir /tmp/higgs_v3_clone \
|
||||
--ref-audio path/to/reference.wav \
|
||||
--ref-text "transcript of the reference clip" \
|
||||
--prompts "Text to synthesize in the cloned voice."
|
||||
```
|
||||
|
||||
## curl example
|
||||
|
||||
```bash
|
||||
curl -X POST http://localhost:8095/v1/audio/speech \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"model": "higgs_audio_v3", "input": "Hello world."}' \
|
||||
--output hello.wav
|
||||
```
|
||||
@@ -0,0 +1,115 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""Batch client for the higgs-audio v3 online server.
|
||||
|
||||
Sends prompts to ``/v1/audio/speech`` and saves the returned WAV files.
|
||||
|
||||
Usage (plain text -> speech):
|
||||
|
||||
python examples/online_serving/text_to_speech/higgs_audio_v3/batch_speech_client.py \
|
||||
--base-url http://localhost:8095 \
|
||||
--output-dir /tmp/higgs_v3_batch \
|
||||
--prompts "Hello world." "The quick brown fox jumps over the lazy dog."
|
||||
|
||||
Usage (voice clone):
|
||||
|
||||
python examples/online_serving/text_to_speech/higgs_audio_v3/batch_speech_client.py \
|
||||
--base-url http://localhost:8095 \
|
||||
--output-dir /tmp/higgs_v3_clone \
|
||||
--ref-audio path/to/reference.wav \
|
||||
--ref-text "the transcript of the reference clip" \
|
||||
--prompts "Hello world."
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import base64
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
DEFAULT_PROMPTS = (
|
||||
"Hello world.",
|
||||
"The quick brown fox jumps over the lazy dog.",
|
||||
"Today is a beautiful day for a walk in the park.",
|
||||
"Innovation distinguishes between a leader and a follower.",
|
||||
)
|
||||
|
||||
|
||||
def _slug(text: str) -> str:
|
||||
import re
|
||||
|
||||
s = re.sub(r"\s+", "_", text.strip().lower())
|
||||
return re.sub(r"[^a-z0-9_]+", "", s)[:32] or "prompt"
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
parser.add_argument("--base-url", default="http://localhost:8095")
|
||||
parser.add_argument("--model", default="higgs_audio_v3")
|
||||
parser.add_argument("--prompts", nargs="+", default=list(DEFAULT_PROMPTS))
|
||||
parser.add_argument("--output-dir", type=Path, default=Path("/tmp/higgs_v3_batch"))
|
||||
parser.add_argument("--format", choices=("wav", "pcm"), default="wav")
|
||||
parser.add_argument("--max-new-tokens", type=int, default=2048)
|
||||
parser.add_argument("--seed", type=int, default=42)
|
||||
parser.add_argument("--timeout-s", type=float, default=120.0)
|
||||
parser.add_argument(
|
||||
"--ref-audio",
|
||||
type=Path,
|
||||
default=None,
|
||||
help="Reference clip for voice clone (WAV/FLAC/MP3 path). Pair with --ref-text.",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--ref-text",
|
||||
type=str,
|
||||
default=None,
|
||||
help="Transcript of the reference clip. Optional but improves fidelity.",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
ref_audio_data_url: str | None = None
|
||||
if args.ref_audio is not None:
|
||||
if not args.ref_audio.exists():
|
||||
print(f"ref-audio file not found: {args.ref_audio}", file=sys.stderr)
|
||||
return 2
|
||||
mime = "audio/wav" if args.ref_audio.suffix.lower() == ".wav" else "audio/mpeg"
|
||||
ref_b64 = base64.b64encode(args.ref_audio.read_bytes()).decode("ascii")
|
||||
ref_audio_data_url = f"data:{mime};base64,{ref_b64}"
|
||||
|
||||
try:
|
||||
import httpx
|
||||
except ImportError:
|
||||
print("this client needs `httpx`. Install with `pip install httpx`.", file=sys.stderr)
|
||||
return 2
|
||||
|
||||
args.output_dir.mkdir(parents=True, exist_ok=True)
|
||||
url = args.base_url.rstrip("/") + "/v1/audio/speech"
|
||||
failures = 0
|
||||
with httpx.Client(timeout=args.timeout_s) as client:
|
||||
for prompt in args.prompts:
|
||||
payload = {
|
||||
"model": args.model,
|
||||
"input": prompt,
|
||||
"response_format": args.format,
|
||||
"max_new_tokens": args.max_new_tokens,
|
||||
"seed": args.seed,
|
||||
}
|
||||
if ref_audio_data_url is not None:
|
||||
payload["ref_audio"] = ref_audio_data_url
|
||||
if args.ref_text:
|
||||
payload["ref_text"] = args.ref_text
|
||||
resp = client.post(url, json=payload)
|
||||
if resp.status_code != 200:
|
||||
print(f"[FAIL] {prompt!r} -> {resp.status_code}: {resp.text[:200]}", file=sys.stderr)
|
||||
failures += 1
|
||||
continue
|
||||
suffix = ".wav" if args.format == "wav" else ".pcm"
|
||||
out = args.output_dir / f"{_slug(prompt)}{suffix}"
|
||||
out.write_bytes(resp.content)
|
||||
print(f"[ ok ] {prompt!r} -> {out} ({len(resp.content)} bytes)")
|
||||
|
||||
return 1 if failures else 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -0,0 +1,32 @@
|
||||
#!/bin/bash
|
||||
# Launch vLLM-Omni server for higgs-audio v3.
|
||||
#
|
||||
# Supports plain text TTS and voice cloning via /v1/audio/speech.
|
||||
#
|
||||
# Usage:
|
||||
# ./run_server.sh # default port 8095, GPU 0
|
||||
# PORT=8096 GPUS=0,1 ./run_server.sh
|
||||
# MODEL=/path/to/local/checkpoint ./run_server.sh
|
||||
|
||||
set -e
|
||||
|
||||
MODEL="${MODEL:-bosonai/higgs-audio-v3-tts-4b}"
|
||||
PORT="${PORT:-8095}"
|
||||
GPUS="${GPUS:-0}"
|
||||
GPU_UTIL="${GPU_UTIL:-0.6}"
|
||||
|
||||
echo "Starting higgs-audio v3 server"
|
||||
echo " MODEL=$MODEL"
|
||||
echo " PORT=$PORT"
|
||||
echo " CUDA_VISIBLE_DEVICES=$GPUS"
|
||||
|
||||
CUDA_VISIBLE_DEVICES="$GPUS" \
|
||||
VLLM_USE_DEEP_GEMM=0 \
|
||||
VLLM_MOE_USE_DEEP_GEMM=0 \
|
||||
vllm-omni serve "$MODEL" \
|
||||
--deploy-config vllm_omni/deploy/higgs_multimodal_qwen3.yaml \
|
||||
--host 0.0.0.0 \
|
||||
--port "$PORT" \
|
||||
--gpu-memory-utilization "$GPU_UTIL" \
|
||||
--trust-remote-code \
|
||||
--omni
|
||||
Reference in new issue
Block a user