[Config Refactor] Migrate 5 TTS models (VoxCPM2 / CosyVoice3 / MiMo Audio / Voxtral TTS / Fish Speech S2 Pro) to Pipeline + Deploy schema (#2958)

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
This commit is contained in:
Yueqian LinandSYLAR authored and GitHub committed 2026-04-21 21:17:53 +08:00
1 parent c2578f7131
commit 3f504b45d2
47 files changed
+702 -844

No files matched your search

@@ -58,7 +58,14 @@ Key components live in `vllm_omni/model_executor/models/cosyvoice3/cosyvoice3.py
- Stage 0 uses `CosyVoice3LM` and outputs speech tokens + conditioning features.
- Stage 1 runs the flow model (DiT-based CFM) and HiFiGAN to synthesize waveform.
Stage wiring is configured in `vllm_omni/model_executor/stage_configs/cosyvoice3.yaml`.
Pipeline topology lives in `vllm_omni/model_executor/models/cosyvoice3/pipeline.py`;
runtime tunables (batch size, memory limits, sampling) live in
`vllm_omni/deploy/cosyvoice3.yaml`. The deploy config auto-loads by
HF `model_type` and defaults to `async_chunk: true` (shared-memory
streaming). Pass `--no-async-chunk` on `vllm serve` to switch to the
legacy sync path where stage 1 runs `text2flow` over the full
speech-token sequence.
- Stage 0 emits latent speech tokens.
- Stage 1 consumes them via `custom_process_input_func` and outputs audio.
- Stage 1 consumes them via `sync_process_input_func` (sync mode) or the
shared-memory connector (async-chunk mode) and outputs audio.
@@ -24,7 +24,13 @@ def run_e2e():
required=True,
help="Path to CosyVoice3 model directory (e.g., pretrained_models/Fun-CosyVoice3-0.5B/).",
)
parser.add_argument("--stage-config", type=str, default="vllm_omni/model_executor/stage_configs/cosyvoice3.yaml")
parser.add_argument(
"--deploy-config",
type=str,
default=None,
help="Override the deploy config path. If unset, auto-loads "
"vllm_omni/deploy/cosyvoice3.yaml based on the HF model_type.",
)
parser.add_argument("--prompt", type=str, default="Hello, this is a test of the CosyVoice system capability.")
parser.add_argument(
"--prompt-text",
@@ -43,18 +49,14 @@ def run_e2e():
if not os.path.exists(args.tokenizer):
raise FileNotFoundError(f"{args.tokenizer} does not exist!")
# Ensure stage config exists
if not os.path.exists(args.stage_config):
raise FileNotFoundError(f"{args.stage_config} does not exist!")
if args.deploy_config is not None and not os.path.exists(args.deploy_config):
raise FileNotFoundError(f"{args.deploy_config} does not exist!")
print(f"Initializing cosyvoice E2E with model={args.model}")
# Initialize Omni
# This spins up the engine(s) based on the stage config
# We pass trust_remote_code=True same as Qwen examples
omni = Omni(
model=args.model,
stage_configs_path=args.stage_config,
deploy_config=args.deploy_config,
trust_remote_code=True,
tokenizer=args.tokenizer,
log_stats=True,
@@ -39,7 +39,6 @@ Run a single sample for basic TTS:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type tts_sft
```
@@ -48,7 +47,6 @@ Run batch samples for basic TTS:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type tts_sft \
--num-prompts {batch_size}
@@ -66,7 +64,6 @@ Generate speech from text input:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type tts_sft \
--text "The weather is so nice today."
@@ -78,7 +75,6 @@ Generate speech with explicit voice style instructions:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type tts_sft_with_instruct \
--text "The weather is so nice today." \
@@ -91,7 +87,6 @@ Generate speech using an audio reference for voice cloning:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type tts_sft_with_audio \
--text "The weather is so nice today." \
@@ -104,7 +99,6 @@ Generate speech from text containing natural voice descriptions:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type tts_sft_with_natural_instruction \
--text "In a panting young male voice, he said: I can't run anymore, wait for me!"
@@ -116,7 +110,6 @@ Transcribe audio to text:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type audio_trancribing_sft \
--audio-path "./spoken_dialogue_assistant_turn_1.wav"
@@ -128,7 +121,6 @@ Understand and analyze audio content with text queries:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type audio_understanding_sft \
--text "Summarize the audio." \
@@ -141,7 +133,6 @@ Audio understanding with reasoning chain:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type audio_understanding_sft_with_thinking \
--text "Summarize the audio." \
@@ -154,7 +145,6 @@ Multi-turn dialogue with audio input and output:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type spoken_dialogue_sft_multiturn \
--audio-path "./prompt_speech_zh_m.wav"
@@ -168,7 +158,6 @@ Multi-turn dialogue converting speech to text:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type speech2text_dialogue_sft_multiturn
```
@@ -181,7 +170,6 @@ Multi-turn text-only dialogue:
```bash
python3 -u end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/mimo_audio.yaml \
--model-name XiaomiMiMo/MiMo-Audio-7B-Instruct \
--query-type text_dialogue_sft_multiturn
```
@@ -182,7 +182,7 @@ def main(args):
omni = Omni(
model=model_name,
stage_configs_path=args.stage_configs_path,
deploy_config=args.deploy_config,
log_stats=args.enable_stats,
log_file=("omni_pipeline.log" if args.enable_stats else None),
init_sleep_seconds=args.init_sleep_seconds,
@@ -428,10 +428,11 @@ def parse_args():
help="Sampling rate for audio.",
)
parser.add_argument(
"--stage-configs-path",
"--deploy-config",
type=str,
default="../../../model_executor/stage_configs/mimo_audio.yaml",
help="Path to a stage configs file.",
default=None,
help="Override the deploy config path. If unset, auto-loads "
"vllm_omni/deploy/mimo_audio.yaml based on the HF model_type.",
)
return parser.parse_args()
@@ -10,28 +10,24 @@ When `mistral_common` has `SpeechRequest` support, prompt token IDs are built vi
```bash
# Basic single-prompt with cheerful_female voice preset
python3 examples/offline_inference/voxtral_tts/end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
--write-audio --voice cheerful_female \
--model mistralai/Voxtral-4B-TTS-2603 \
--text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
# 32 replicate prompts with cheerful_female voice preset
python3 examples/offline_inference/voxtral_tts/end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
--num-prompts 32 --write-audio --voice cheerful_female \
--model mistralai/Voxtral-4B-TTS-2603 \
--text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
# Streaming with neutral_female voice preset
python3 examples/offline_inference/voxtral_tts/end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
--streaming --write-audio --voice neutral_female \
--model mistralai/Voxtral-4B-TTS-2603 \
--text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
# 32 prompts, 8 concurrent requests per wave, streaming with neutral_female voice
python3 examples/offline_inference/voxtral_tts/end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
--num-prompts 32 --concurrency 8 --streaming --write-audio --voice neutral_female \
--model mistralai/Voxtral-4B-TTS-2603 \
--text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
@@ -39,7 +35,6 @@ python3 examples/offline_inference/voxtral_tts/end2end.py \
# Short debug prompt with reference audio
# Note: Reference audio capability is not yet released.
python3 examples/offline_inference/voxtral_tts/end2end.py \
--stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
--write-audio \
--model mistralai/Voxtral-4B-TTS-2603 \
--text "This is a test message." \
@@ -54,7 +49,7 @@ python3 examples/offline_inference/voxtral_tts/end2end.py \
| `--text TEXT` | Text to synthesize (default: `"This is a test message."`) |
| `--audio-path PATH` | Path to reference audio file for voice cloning |
| `--output-dir DIR` | Directory to write output WAV files (default: `output_audio`) |
| `--stage-configs-path PATH` | Path to stage configs YAML (currently it must be set for VoxtralTTS) |
| `--deploy-config PATH` | Override the deploy config path. If unset, auto-loads `vllm_omni/deploy/voxtral_tts.yaml` from the HF `model_type`. |
| `--num-prompts N` | Number of replicate prompts to run for measuring performance (default: 1) |
| `--streaming` | Use streaming generation via `AsyncOmni` (default: blocking `Omni`) |
| `--concurrency N` | Max concurrent requests per wave (must be used with `--streaming`, must evenly divide `--num-prompts`) |
@@ -39,7 +39,7 @@ logger = logging.getLogger(__name__)
async def run_streaming(inputs, sampling_params_list, model_name, args, output_dir):
async_omni = AsyncOmni(
model=model_name,
stage_configs_path=args.stage_configs_path,
deploy_config=args.deploy_config,
log_stats=args.log_stats,
)
@@ -192,7 +192,7 @@ def run_non_streaming(inputs, sampling_params_list, model_name, args, output_dir
llm = Omni(
model=model_name,
log_stats=args.log_stats,
stage_configs_path=args.stage_configs_path,
deploy_config=args.deploy_config,
)
if args.profiling_mode:
@@ -253,10 +253,11 @@ def parse_args() -> Namespace:
help="Directory to write output wav files.",
)
parser.add_argument(
"--stage-configs-path",
"--deploy-config",
type=str,
default=None,
help="Path to stage configs YAML. Auto-resolved from model if not set.",
help="Override the deploy config path. If unset, auto-loads "
"vllm_omni/deploy/voxtral_tts.yaml based on the HF model_type.",
)
parser.add_argument(
"--num-prompts", type=int, default=1, help="Number of replicate prompts to run for measuring performance"