[Higgs-Audio] bosonai/higgs-audio-v2-generation-3B-base TTS model support (#3762)

Signed-off-by: Yuekai Zhang <zhangyuekai@foxmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>

examples/offline_inference/text_to_speech/higgs_audio_v2/README.md

@@ -0,0 +1,38 @@
+# higgs-audio v2 — offline example
+
+Drives Stage 0 (DualFFN talker) + Stage 1 (HiggsAudio codec) for `bosonai/higgs-audio-v2-generation-3B-base` end-to-end through the vLLM-Omni engine and writes a 24 kHz mono WAV per prompt.
+
+## Prerequisites
+
+Voice clone needs `transformers>=5.3.0` — vllm-omni loads the audio codec via HF's `HiggsAudioV2TokenizerModel`, instantiated from the `k2-fsa/OmniVoice/audio_tokenizer/` subdirectory (only that ~806 MB subdir is downloaded). The boson-ai standalone tokenizer repo's `model.safetensors` is actually a copy of the 3B talker LM, so HF can't load it directly; the k2 bundle ships the same codec weights repackaged with HF-compatible key naming.
+
+```bash
+pip install -U "transformers>=5.3.0"
+```
+
+## Quick start
+
+Plain TTS:
+```bash
+python examples/offline_inference/text_to_speech/higgs_audio_v2/end2end.py \
+    --texts "Hello world." "The quick brown fox jumps over the lazy dog." \
+    --output-dir results/wavs
+```
+
+## Voice cloning
+
+Pass both `--ref-audio` and `--ref-text` together:
+```bash
+python examples/offline_inference/text_to_speech/higgs_audio_v2/end2end.py \
+    --texts "Hello, this is a cloned voice." \
+    --ref-audio /path/to/reference.wav \
+    --ref-text  "Exact transcript spoken in reference.wav." \
+    --output-dir results/wavs
+```
+
+## Notes
+
+- Output: 24 kHz mono WAV.
+- Deploy config: `vllm_omni/deploy/higgs_audio_v2.yaml` (auto-loaded by HF `model_type`).
+- `--ref-text` must be the real transcript of `--ref-audio`; mismatched text degrades cloned-voice quality.
+- For online serving, see [`examples/online_serving/text_to_speech/higgs_audio_v2/`](../../../online_serving/text_to_speech/higgs_audio_v2/).

examples/offline_inference/text_to_speech/higgs_audio_v2/end2end.py

@@ -0,0 +1,205 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Offline higgs-audio v2 inference example.
+
+Runs Stage 0 (DualFFN talker) + Stage 1 (HiggsAudio codec) end-to-end
+through the vLLM-Omni engine without going through the HTTP server, and
+saves a 24 kHz mono WAV per prompt.
+
+Example:
+
+    python examples/offline_inference/text_to_speech/higgs_audio_v2/end2end.py \\
+        --texts "Hello world." \\
+                "The quick brown fox jumps over the lazy dog." \\
+        --output-dir results/wavs
+"""
+
+from __future__ import annotations
+
+import os
+
+# DeepGEMM FP8 kernels require an optional backend that may not be installed.
+# Disable the warmup before importing vLLM so engine startup falls back to the
+# regular gemm path. Users with deep_gemm installed can override these.
+os.environ.setdefault("VLLM_USE_DEEP_GEMM", "0")
+os.environ.setdefault("VLLM_MOE_USE_DEEP_GEMM", "0")
+
+import time
+from pathlib import Path
+
+import numpy as np
+import soundfile as sf
+import torch
+from vllm.utils.argparse_utils import FlexibleArgumentParser
+
+from vllm_omni import Omni
+from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
+
+SAMPLE_RATE = 24_000
+DEFAULT_TEXTS = (
+    "Hello world.",
+    "The quick brown fox jumps over the lazy dog.",
+)
+
+
+def parse_args():
+    parser = FlexibleArgumentParser(description="Offline higgs-audio v2 inference")
+    parser.add_argument(
+        "--model",
+        type=str,
+        default="bosonai/higgs-audio-v2-generation-3B-base",
+        help="Stage-0 talker model id or path.",
+    )
+    parser.add_argument(
+        "--texts",
+        type=str,
+        nargs="+",
+        default=list(DEFAULT_TEXTS),
+        help="One or more plain-text prompts to synthesize.",
+    )
+    parser.add_argument(
+        "--output-dir",
+        type=str,
+        default="results/wavs",
+        help="Directory to write per-prompt WAV files.",
+    )
+    parser.add_argument(
+        "--deploy-config",
+        type=str,
+        default=None,
+        help="Override the deploy config path. Auto-loads "
+        "vllm_omni/deploy/higgs_audio_v2.yaml from the HF model_type by default.",
+    )
+    parser.add_argument(
+        "--max-new-tokens",
+        type=int,
+        default=500,
+        help="Cap on Stage-0 codec frames per request.",
+    )
+    parser.add_argument(
+        "--ref-audio",
+        type=str,
+        default=None,
+        help="Reference clip for voice clone (path to a WAV file). Paired with --ref-text.",
+    )
+    parser.add_argument(
+        "--ref-text",
+        type=str,
+        default=None,
+        help="Transcript of the reference clip. Required when --ref-audio is set.",
+    )
+    nullify_stage_engine_defaults(parser)
+    return parser.parse_args()
+
+
+def _slugify(text: str) -> str:
+    import re
+
+    slug = re.sub(r"\s+", "_", text.strip().lower())
+    slug = re.sub(r"[^a-z0-9_]+", "", slug)
+    return slug[:48] or "prompt"
+
+
+def _extract_pcm(multimodal_output: dict) -> torch.Tensor:
+    """Pull the final concatenated PCM tensor out of a request's multimodal_output."""
+    audio = multimodal_output.get("model_outputs")
+    if audio is None:
+        audio = multimodal_output.get("audio")
+    if audio is None:
+        raise ValueError(f"no audio key in multimodal_output: {list(multimodal_output.keys())}")
+    if isinstance(audio, list):
+        valid = [torch.as_tensor(a).float().cpu().reshape(-1) for a in audio if a is not None]
+        if not valid:
+            raise ValueError("audio list is empty")
+        return torch.cat(valid, dim=0) if len(valid) > 1 else valid[0]
+    return torch.as_tensor(audio).float().cpu().reshape(-1)
+
+
+def _pcm_to_int16(pcm: torch.Tensor) -> np.ndarray:
+    arr = pcm.numpy()
+    if arr.dtype.kind == "f":
+        arr = np.clip(arr, -1.0, 1.0)
+        arr = (arr * 32767.0).astype(np.int16)
+    else:
+        arr = arr.astype(np.int16)
+    return arr
+
+
+def main():
+    args = parse_args()
+    if (args.ref_audio is None) != (args.ref_text is None):
+        raise SystemExit("--ref-audio and --ref-text must be supplied together")
+    output_dir = Path(args.output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    engine = Omni(model=args.model, deploy_config=args.deploy_config)
+
+    # Build prompt_token_ids using the same path serving_speech.py takes online.
+    from transformers import AutoProcessor
+
+    from vllm_omni.model_executor.models.higgs_audio_v2.higgs_audio_v2_tokenizer import (
+        build_plain_text_prompt,
+        build_voice_clone_prompt,
+        input_ids_to_python_list,
+    )
+
+    processor = AutoProcessor.from_pretrained(args.model, trust_remote_code=True)
+
+    # Voice-clone path: load the reference clip once. The HF processor will
+    # encode it via the bundled HiggsAudioV2TokenizerModel each time we build
+    # a prompt below. This is cheap on CPU for a few-second clip.
+    ref_wav: np.ndarray | None = None
+    ref_sr: int | None = None
+    if args.ref_audio is not None:
+        ref_wav, ref_sr = sf.read(args.ref_audio, always_2d=False)
+        if ref_wav.ndim == 2:
+            ref_wav = ref_wav.mean(axis=1)
+
+    print(f"Model       : {args.model}")
+    print(f"Prompts     : {len(args.texts)}")
+    print(f"Output dir  : {output_dir}")
+    print(f"Voice clone : {'yes' if ref_wav is not None else 'no'}")
+
+    # Run one prompt at a time. The Stage-0 talker's per-slot audio state is
+    # request-scoped; submitting multiple prompts in the same engine.generate()
+    # call would batch them in the AR runner and exercise a code path that is
+    # not validated for this model yet.
+    total_elapsed = 0.0
+    total_dur = 0.0
+    for text in args.texts:
+        if ref_wav is not None:
+            out = build_voice_clone_prompt(processor, text, ref_wav, int(ref_sr), args.ref_text)
+            prompt = {
+                "prompt_token_ids": out["prompt_token_ids"],
+                # Bare tensors (NOT list-wrapped): the msgspec serializer in
+                # vllm_omni.data_entry_keys routes torch.Tensor → tensor_data
+                # and list[Tensor] → list_data (which silently strips tensors).
+                "additional_information": {
+                    "audio_input_ids": out["audio_input_ids"],
+                    "audio_input_ids_mask": out["audio_input_ids_mask"],
+                },
+            }
+        else:
+            inputs = build_plain_text_prompt(processor, text)
+            prompt = {"prompt_token_ids": input_ids_to_python_list(inputs)}
+        t_start = time.perf_counter()
+        outputs = engine.generate([prompt])
+        elapsed = time.perf_counter() - t_start
+        total_elapsed += elapsed
+
+        mm = outputs[0].outputs[0].multimodal_output
+        pcm = _extract_pcm(mm)
+        slug = _slugify(text)
+        out_path = output_dir / f"{slug}.wav"
+        sf.write(str(out_path), _pcm_to_int16(pcm), SAMPLE_RATE, format="WAV", subtype="PCM_16")
+        dur = pcm.numel() / SAMPLE_RATE
+        total_dur += dur
+        print(f"  {slug:<50} dur={dur:5.2f}s  -> {out_path}")
+
+    rtf = total_elapsed / total_dur if total_dur > 0 else float("inf")
+    print(f"Total infer : {total_elapsed:.2f}s  total audio: {total_dur:.2f}s  RTF: {rtf:.3f}")
+
+
+if __name__ == "__main__":
+    os.environ.setdefault("VLLM_WORKER_MULTIPROC_METHOD", "spawn")
+    main()

examples/online_serving/text_to_speech/higgs_audio_v2/README.md

@@ -0,0 +1,63 @@
+# higgs-audio v2 online example
+
+This directory contains the online-serving entry points for boson-ai's higgs-audio v2 as integrated by vllm-omni: a 2-stage TTS pipeline (Llama-3.2-3B talker with DualFFN audio expert + HiggsAudio codec decoder) emitting 24 kHz mono speech.
+
+## Prerequisites
+
+Voice clone uses HF's `HiggsAudioV2TokenizerModel` loaded from `k2-fsa/OmniVoice/audio_tokenizer/` (the boson-ai standalone tokenizer Hub repo's `model.safetensors` is the 3B talker LM, not the codec). Only that ~806 MB subdir is downloaded.
+
+```bash
+pip install -U "transformers>=5.3.0"
+```
+
+## Files
+
+- `run_server.sh` — launch the vllm-omni server with the bundled `vllm_omni/deploy/higgs_audio_v2.yaml` deploy config.
+- `batch_speech_client.py` — send a list of prompts to `/v1/audio/speech` and save the returned WAV / PCM bytes to a directory; optionally passes `--ref-audio` + `--ref-text` for shallow voice clone.
+
+## Launching the server
+
+```bash
+GPUS=6,7 PORT=8094 bash examples/online_serving/text_to_speech/higgs_audio_v2/run_server.sh
+```
+
+Environment overrides:
+
+- `MODEL` — HF id of the talker (default `bosonai/higgs-audio-v2-generation-3B-base`).
+- `PORT` — server port (default `8094`).
+- `GPUS` — `CUDA_VISIBLE_DEVICES` value (default `6,7`).
+- `GPU_UTIL` — `--gpu-memory-utilization` (default `0.4`).
+
+The script also exports `VLLM_USE_DEEP_GEMM=0` / `VLLM_MOE_USE_DEEP_GEMM=0` so the example works on images without the optional `deep_gemm` backend.
+
+The deploy YAML ships with `async_chunk: false` and `codec_streaming: true`, i.e. Stage 0 finishes its codec frames before Stage 1 starts decoding, and Stage 1 streams WAV/PCM bytes to the client chunk-by-chunk.
+
+## Driving the server
+
+Plain TTS:
+
+```bash
+python examples/online_serving/text_to_speech/higgs_audio_v2/batch_speech_client.py \
+    --base-url http://localhost:8094 \
+    --model bosonai/higgs-audio-v2-generation-3B-base \
+    --output-dir /tmp/higgs_audio_v2_batch \
+    --prompts "Hello world." \
+              "The quick brown fox jumps over the lazy dog."
+```
+
+Voice clone — pass a reference clip and its transcript (both required together):
+
+```bash
+python examples/online_serving/text_to_speech/higgs_audio_v2/batch_speech_client.py \
+    --base-url http://localhost:8094 \
+    --model bosonai/higgs-audio-v2-generation-3B-base \
+    --output-dir /tmp/higgs_audio_v2_clone \
+    --ref-audio /path/to/reference.wav \
+    --ref-text  "Exact transcript spoken in reference.wav." \
+    --prompts "Hello, this is a cloned voice."
+```
+
+## Notes
+
+- `--ref-text` must be the real transcript of `--ref-audio`; mismatched text degrades cloned-voice quality.
+- Out of scope (rejected with explicit 4xx by the request validator): multi-speaker `[SPEAKERn]` tags inside `input`, `profile:` text-only speaker descriptions, the `ref_audio_in_system_message` system-block variant, chunked long-form generation, and per-request `voice` / `instructions` / `task_type` / `language` / `speed != 1.0` / `x_vector_only_mode` / `speaker_embedding`.

examples/online_serving/text_to_speech/higgs_audio_v2/batch_speech_client.py

@@ -0,0 +1,122 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Batch client for the higgs-audio v2 online server.
+
+Sends a fixed list of prompts to ``/v1/audio/speech`` and saves the returned
+WAV files (or raw PCM bytes when ``--format pcm``) into ``--output-dir``.
+
+Usage (plain text -> speech):
+
+  python examples/online_serving/text_to_speech/higgs_audio_v2/batch_speech_client.py \
+      --base-url http://localhost:8094 \
+      --output-dir /tmp/higgs_audio_v2_batch \
+      --prompts "Hello world." "The quick brown fox jumps over the lazy dog."
+
+Usage (shallow voice clone — pass a reference clip + its transcript):
+
+  python examples/online_serving/text_to_speech/higgs_audio_v2/batch_speech_client.py \
+      --base-url http://localhost:8094 \
+      --output-dir /tmp/higgs_audio_v2_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.",
+    "It was the night before my birthday.",
+    "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:8094")
+    parser.add_argument("--model", default="higgs_audio_v2")
+    parser.add_argument("--prompts", nargs="+", default=list(DEFAULT_PROMPTS))
+    parser.add_argument("--output-dir", type=Path, default=Path("/tmp/higgs_audio_v2_batch"))
+    parser.add_argument("--format", choices=("wav", "pcm"), default="wav")
+    parser.add_argument("--max-new-tokens", type=int, default=300)
+    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 (path to a WAV file). Must be paired with --ref-text.",
+    )
+    parser.add_argument(
+        "--ref-text",
+        type=str,
+        default=None,
+        help="Transcript of the reference clip. Required when --ref-audio is set.",
+    )
+    args = parser.parse_args()
+
+    if (args.ref_audio is None) != (args.ref_text is None):
+        print("--ref-audio and --ref-text must be supplied together", file=sys.stderr)
+        return 2
+
+    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
+                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())

examples/online_serving/text_to_speech/higgs_audio_v2/run_server.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+# Launch vLLM-Omni server for higgs-audio v2.
+#
+# v1 scope: plain text -> 24 kHz speech only. Voice cloning, multi-speaker,
+# ChatML rich content, and language overrides are rejected by the validator
+# with explicit 4xx (see vllm_omni/entrypoints/openai/serving_speech.py).
+#
+# Usage:
+#   ./run_server.sh                 # default port 8094, GPUs 6 and 7
+#   PORT=8095 GPUS=6,7 ./run_server.sh
+#   MODEL=bosonai/higgs-audio-v2-generation-3B-base ./run_server.sh
+
+set -e
+
+MODEL="${MODEL:-bosonai/higgs-audio-v2-generation-3B-base}"
+PORT="${PORT:-8094}"
+GPUS="${GPUS:-6,7}"
+GPU_UTIL="${GPU_UTIL:-0.4}"
+
+echo "Starting higgs-audio v2 server"
+echo "  MODEL=$MODEL"
+echo "  PORT=$PORT"
+echo "  CUDA_VISIBLE_DEVICES=$GPUS"
+
+# DeepGEMM FP8 kernels are optional and trip warmup on builds without
+# the deep_gemm backend; disable them so the example works out of the box.
+# Users with deep_gemm installed can re-enable via the same env vars.
+CUDA_VISIBLE_DEVICES="$GPUS" \
+VLLM_USE_DEEP_GEMM=0 \
+VLLM_MOE_USE_DEEP_GEMM=0 \
+vllm-omni serve "$MODEL" \
+    --deploy-config vllm_omni/deploy/higgs_audio_v2.yaml \
+    --host 0.0.0.0 \
+    --port "$PORT" \
+    --gpu-memory-utilization "$GPU_UTIL" \
+    --trust-remote-code \
+    --omni