mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-12 19:30:38 -07:00
add HumeAI TADA TTS engine (1B English + 3B Multilingual)
Integrates HumeAI's TADA (Text-Acoustic Dual Alignment) speech-language model as a new TTS engine. TADA uses a novel 1:1 token-audio alignment that produces coherent speech over long sequences (700s+). Two model variants: - tada-1b: English-only, ~4GB, built on Llama 3.2 1B - tada-3b-ml: 10 languages, ~8GB, built on Llama 3.2 3B Backend uses the Encoder for voice prompt encoding with caching, and TadaForCausalLM with flow-matching diffusion for generation. Supports bf16 inference on CUDA, forces CPU on macOS (MPS compatibility). Installed with --no-deps due to torch>=2.7 pin conflict; descript-audio-codec and torchaudio added as explicit sub-dependencies.
This commit is contained in:
James Pine
@@ -62,6 +62,7 @@ jobs:
|
||||
pip install pyinstaller
|
||||
pip install -r backend/requirements.txt
|
||||
pip install --no-deps chatterbox-tts
|
||||
pip install --no-deps hume-tada
|
||||
|
||||
- name: Install MLX dependencies (Apple Silicon only)
|
||||
if: matrix.backend == 'mlx'
|
||||
@@ -188,6 +189,7 @@ jobs:
|
||||
pip install pyinstaller
|
||||
pip install -r backend/requirements.txt
|
||||
pip install --no-deps chatterbox-tts
|
||||
pip install --no-deps hume-tada
|
||||
|
||||
- name: Install PyTorch with CUDA 12.6
|
||||
run: |
|
||||
|
||||
@@ -35,6 +35,8 @@ RUN pip install --no-cache-dir --upgrade pip
|
||||
|
||||
COPY backend/requirements.txt .
|
||||
RUN pip install --no-cache-dir --prefix=/install -r requirements.txt
|
||||
RUN pip install --no-cache-dir --prefix=/install --no-deps chatterbox-tts
|
||||
RUN pip install --no-cache-dir --prefix=/install --no-deps hume-tada
|
||||
RUN pip install --no-cache-dir --prefix=/install \
|
||||
git+https://github.com/QwenLM/Qwen3-TTS.git
|
||||
|
||||
|
||||
@@ -20,6 +20,8 @@ const ENGINE_OPTIONS = [
|
||||
{ value: 'luxtts', label: 'LuxTTS' },
|
||||
{ value: 'chatterbox', label: 'Chatterbox' },
|
||||
{ value: 'chatterbox_turbo', label: 'Chatterbox Turbo' },
|
||||
{ value: 'tada:1B', label: 'TADA 1B' },
|
||||
{ value: 'tada:3B', label: 'TADA 3B Multilingual' },
|
||||
] as const;
|
||||
|
||||
const ENGINE_DESCRIPTIONS: Record<string, string> = {
|
||||
@@ -27,6 +29,7 @@ const ENGINE_DESCRIPTIONS: Record<string, string> = {
|
||||
luxtts: 'Fast, English-focused',
|
||||
chatterbox: '23 languages, incl. Hebrew',
|
||||
chatterbox_turbo: 'English, [laugh] [cough] tags',
|
||||
tada: 'HumeAI, 700s+ coherent audio',
|
||||
};
|
||||
|
||||
/** Engines that only support English and should force language to 'en' on select. */
|
||||
@@ -34,6 +37,7 @@ const ENGLISH_ONLY_ENGINES = new Set(['luxtts', 'chatterbox_turbo']);
|
||||
|
||||
function getSelectValue(engine: string, modelSize?: string): string {
|
||||
if (engine === 'qwen') return `qwen:${modelSize || '1.7B'}`;
|
||||
if (engine === 'tada') return `tada:${modelSize || '1B'}`;
|
||||
return engine;
|
||||
}
|
||||
|
||||
@@ -48,6 +52,20 @@ function handleEngineChange(form: UseFormReturn<GenerationFormValues>, value: st
|
||||
if (!available.some((l) => l.value === currentLang)) {
|
||||
form.setValue('language', available[0]?.value ?? 'en');
|
||||
}
|
||||
} else if (value.startsWith('tada:')) {
|
||||
const [, modelSize] = value.split(':');
|
||||
form.setValue('engine', 'tada');
|
||||
form.setValue('modelSize', modelSize as '1B' | '3B');
|
||||
// TADA 1B is English-only; 3B is multilingual
|
||||
if (modelSize === '1B') {
|
||||
form.setValue('language', 'en');
|
||||
} else {
|
||||
const currentLang = form.getValues('language');
|
||||
const available = getLanguageOptionsForEngine('tada');
|
||||
if (!available.some((l) => l.value === currentLang)) {
|
||||
form.setValue('language', available[0]?.value ?? 'en');
|
||||
}
|
||||
}
|
||||
} else {
|
||||
form.setValue('engine', value as GenerationFormValues['engine']);
|
||||
form.setValue('modelSize', undefined as unknown as '1.7B' | '0.6B');
|
||||
|
||||
@@ -62,6 +62,10 @@ const MODEL_DESCRIPTIONS: Record<string, string> = {
|
||||
'Production-grade open source TTS by Resemble AI. Supports 23 languages with voice cloning and emotion exaggeration control.',
|
||||
'chatterbox-turbo':
|
||||
'Streamlined 350M parameter TTS by Resemble AI. High-quality English speech with less compute and VRAM than larger models.',
|
||||
'tada-1b':
|
||||
'HumeAI TADA 1B — English speech-language model built on Llama 3.2 1B. Generates 700s+ of coherent audio with synchronized text-acoustic alignment.',
|
||||
'tada-3b-ml':
|
||||
'HumeAI TADA 3B Multilingual — built on Llama 3.2 3B. Supports 10 languages with high-fidelity voice cloning via text-acoustic dual alignment.',
|
||||
'whisper-base':
|
||||
'Smallest Whisper model (74M parameters). Fast transcription with moderate accuracy.',
|
||||
'whisper-small':
|
||||
@@ -391,7 +395,8 @@ export function ModelManagement() {
|
||||
(m) =>
|
||||
m.model_name.startsWith('qwen-tts') ||
|
||||
m.model_name.startsWith('luxtts') ||
|
||||
m.model_name.startsWith('chatterbox'),
|
||||
m.model_name.startsWith('chatterbox') ||
|
||||
m.model_name.startsWith('tada'),
|
||||
) ?? [];
|
||||
const whisperModels = modelStatus?.models.filter((m) => m.model_name.startsWith('whisper')) ?? [];
|
||||
|
||||
|
||||
@@ -42,8 +42,8 @@ export interface GenerationRequest {
|
||||
text: string;
|
||||
language: LanguageCode;
|
||||
seed?: number;
|
||||
model_size?: '1.7B' | '0.6B';
|
||||
engine?: 'qwen' | 'luxtts' | 'chatterbox' | 'chatterbox_turbo';
|
||||
model_size?: '1.7B' | '0.6B' | '1B' | '3B';
|
||||
engine?: 'qwen' | 'luxtts' | 'chatterbox' | 'chatterbox_turbo' | 'tada';
|
||||
instruct?: string;
|
||||
max_chunk_chars?: number;
|
||||
crossfade_ms?: number;
|
||||
|
||||
@@ -66,6 +66,7 @@ export const ENGINE_LANGUAGES: Record<string, readonly LanguageCode[]> = {
|
||||
'zh',
|
||||
],
|
||||
chatterbox_turbo: ['en'],
|
||||
tada: ['en', 'ar', 'zh', 'de', 'es', 'fr', 'it', 'ja', 'pl', 'pt'],
|
||||
} as const;
|
||||
|
||||
/** Helper: get language options for a given engine. */
|
||||
|
||||
@@ -15,9 +15,9 @@ const generationSchema = z.object({
|
||||
text: z.string().min(1, '').max(50000),
|
||||
language: z.enum(LANGUAGE_CODES as [LanguageCode, ...LanguageCode[]]),
|
||||
seed: z.number().int().optional(),
|
||||
modelSize: z.enum(['1.7B', '0.6B']).optional(),
|
||||
modelSize: z.enum(['1.7B', '0.6B', '1B', '3B']).optional(),
|
||||
instruct: z.string().max(500).optional(),
|
||||
engine: z.enum(['qwen', 'luxtts', 'chatterbox', 'chatterbox_turbo']).optional(),
|
||||
engine: z.enum(['qwen', 'luxtts', 'chatterbox', 'chatterbox_turbo', 'tada']).optional(),
|
||||
});
|
||||
|
||||
export type GenerationFormValues = z.infer<typeof generationSchema>;
|
||||
@@ -79,7 +79,9 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
|
||||
? 'chatterbox-tts'
|
||||
: engine === 'chatterbox_turbo'
|
||||
? 'chatterbox-turbo'
|
||||
: `qwen-tts-${data.modelSize}`;
|
||||
: engine === 'tada'
|
||||
? `tada-${(data.modelSize || '1B').toLowerCase()}`
|
||||
: `qwen-tts-${data.modelSize}`;
|
||||
const displayName =
|
||||
engine === 'luxtts'
|
||||
? 'LuxTTS'
|
||||
@@ -87,9 +89,13 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
|
||||
? 'Chatterbox TTS'
|
||||
: engine === 'chatterbox_turbo'
|
||||
? 'Chatterbox Turbo'
|
||||
: data.modelSize === '1.7B'
|
||||
? 'Qwen TTS 1.7B'
|
||||
: 'Qwen TTS 0.6B';
|
||||
: engine === 'tada'
|
||||
? data.modelSize === '3B'
|
||||
? 'TADA 3B Multilingual'
|
||||
: 'TADA 1B'
|
||||
: data.modelSize === '1.7B'
|
||||
? 'Qwen TTS 1.7B'
|
||||
: 'Qwen TTS 0.6B';
|
||||
|
||||
// Check if model needs downloading
|
||||
try {
|
||||
@@ -104,7 +110,7 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
|
||||
console.error('Failed to check model status:', error);
|
||||
}
|
||||
|
||||
const isQwen = engine === 'qwen';
|
||||
const hasModelSizes = engine === 'qwen' || engine === 'tada';
|
||||
const effectsChain = options.getEffectsChain?.();
|
||||
// This now returns immediately with status="generating"
|
||||
const result = await generation.mutateAsync({
|
||||
@@ -112,9 +118,9 @@ export function useGenerationForm(options: UseGenerationFormOptions = {}) {
|
||||
text: data.text,
|
||||
language: data.language,
|
||||
seed: data.seed,
|
||||
model_size: isQwen ? data.modelSize : undefined,
|
||||
model_size: hasModelSizes ? data.modelSize : undefined,
|
||||
engine,
|
||||
instruct: isQwen ? data.instruct || undefined : undefined,
|
||||
instruct: engine === 'qwen' ? data.instruct || undefined : undefined,
|
||||
max_chunk_chars: maxChunkChars,
|
||||
crossfade_ms: crossfadeMs,
|
||||
normalize: normalizeAudio,
|
||||
|
||||
@@ -166,6 +166,7 @@ TTS_ENGINES = {
|
||||
"luxtts": "LuxTTS",
|
||||
"chatterbox": "Chatterbox TTS",
|
||||
"chatterbox_turbo": "Chatterbox Turbo",
|
||||
"tada": "TADA",
|
||||
}
|
||||
|
||||
|
||||
@@ -259,6 +260,24 @@ def _get_non_qwen_tts_configs() -> list[ModelConfig]:
|
||||
needs_trim=True,
|
||||
languages=["en"],
|
||||
),
|
||||
ModelConfig(
|
||||
model_name="tada-1b",
|
||||
display_name="TADA 1B (English)",
|
||||
engine="tada",
|
||||
hf_repo_id="HumeAI/tada-1b",
|
||||
model_size="1B",
|
||||
size_mb=4000,
|
||||
languages=["en"],
|
||||
),
|
||||
ModelConfig(
|
||||
model_name="tada-3b-ml",
|
||||
display_name="TADA 3B Multilingual",
|
||||
engine="tada",
|
||||
hf_repo_id="HumeAI/tada-3b-ml",
|
||||
model_size="3B",
|
||||
size_mb=8000,
|
||||
languages=["en", "ar", "zh", "de", "es", "fr", "it", "ja", "pl", "pt"],
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
@@ -339,10 +358,12 @@ def engine_has_model_sizes(engine: str) -> bool:
|
||||
|
||||
|
||||
async def load_engine_model(engine: str, model_size: str = "default") -> None:
|
||||
"""Load a model for the given engine, handling the Qwen model_size special case."""
|
||||
"""Load a model for the given engine, handling engines with multiple model sizes."""
|
||||
backend = get_tts_backend_for_engine(engine)
|
||||
if engine == "qwen":
|
||||
await backend.load_model_async(model_size)
|
||||
elif engine == "tada":
|
||||
await backend.load_model(model_size)
|
||||
else:
|
||||
await backend.load_model()
|
||||
|
||||
@@ -358,7 +379,7 @@ async def ensure_model_cached_or_raise(engine: str, model_size: str = "default")
|
||||
cfg = c
|
||||
break
|
||||
|
||||
if engine == "qwen":
|
||||
if engine in ("qwen", "tada"):
|
||||
if not backend._is_model_cached(model_size):
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
@@ -490,6 +511,10 @@ def get_tts_backend_for_engine(engine: str) -> TTSBackend:
|
||||
from .chatterbox_turbo_backend import ChatterboxTurboTTSBackend
|
||||
|
||||
backend = ChatterboxTurboTTSBackend()
|
||||
elif engine == "tada":
|
||||
from .hume_backend import HumeTadaBackend
|
||||
|
||||
backend = HumeTadaBackend()
|
||||
else:
|
||||
raise ValueError(f"Unknown TTS engine: {engine}. Supported: {list(TTS_ENGINES.keys())}")
|
||||
|
||||
|
||||
@@ -0,0 +1,310 @@
|
||||
"""
|
||||
HumeAI TADA TTS backend implementation.
|
||||
|
||||
Wraps HumeAI's TADA (Text-Acoustic Dual Alignment) model for
|
||||
high-quality voice cloning. Two model variants:
|
||||
- tada-1b: English-only, ~2B params (Llama 3.2 1B base)
|
||||
- tada-3b-ml: Multilingual, ~4B params (Llama 3.2 3B base)
|
||||
|
||||
Both use a shared encoder/codec (HumeAI/tada-codec). The encoder
|
||||
produces 1:1 aligned token embeddings from reference audio, and the
|
||||
causal LM generates speech via flow-matching diffusion.
|
||||
|
||||
24kHz output, bf16 inference on CUDA, fp32 on CPU.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
import threading
|
||||
from typing import ClassVar, List, Optional, Tuple
|
||||
|
||||
import numpy as np
|
||||
|
||||
from . import TTSBackend
|
||||
from .base import (
|
||||
is_model_cached,
|
||||
get_torch_device,
|
||||
combine_voice_prompts as _combine_voice_prompts,
|
||||
model_load_progress,
|
||||
)
|
||||
from ..utils.cache import get_cache_key, get_cached_voice_prompt, cache_voice_prompt
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# HuggingFace repos
|
||||
TADA_CODEC_REPO = "HumeAI/tada-codec"
|
||||
TADA_1B_REPO = "HumeAI/tada-1b"
|
||||
TADA_3B_ML_REPO = "HumeAI/tada-3b-ml"
|
||||
|
||||
TADA_MODEL_REPOS = {
|
||||
"1B": TADA_1B_REPO,
|
||||
"3B": TADA_3B_ML_REPO,
|
||||
}
|
||||
|
||||
# Key weight files for cache detection
|
||||
_TADA_MODEL_WEIGHT_FILES = [
|
||||
"model.safetensors",
|
||||
]
|
||||
|
||||
_TADA_CODEC_WEIGHT_FILES = [
|
||||
"encoder/model.safetensors",
|
||||
]
|
||||
|
||||
|
||||
class HumeTadaBackend:
|
||||
"""HumeAI TADA TTS backend for high-quality voice cloning."""
|
||||
|
||||
_load_lock: ClassVar[threading.Lock] = threading.Lock()
|
||||
|
||||
def __init__(self):
|
||||
self.model = None
|
||||
self.encoder = None
|
||||
self.model_size = "1B" # default to 1B
|
||||
self._device = None
|
||||
self._model_load_lock = asyncio.Lock()
|
||||
|
||||
def _get_device(self) -> str:
|
||||
# Force CPU on macOS — MPS has issues with flow matching
|
||||
# and large vocab lm_head (>65536 output channels)
|
||||
return get_torch_device(force_cpu_on_mac=True)
|
||||
|
||||
def is_loaded(self) -> bool:
|
||||
return self.model is not None
|
||||
|
||||
def _get_model_path(self, model_size: str = "1B") -> str:
|
||||
return TADA_MODEL_REPOS.get(model_size, TADA_1B_REPO)
|
||||
|
||||
def _is_model_cached(self, model_size: str = "1B") -> bool:
|
||||
repo = TADA_MODEL_REPOS.get(model_size, TADA_1B_REPO)
|
||||
model_cached = is_model_cached(repo, required_files=_TADA_MODEL_WEIGHT_FILES)
|
||||
codec_cached = is_model_cached(TADA_CODEC_REPO, required_files=_TADA_CODEC_WEIGHT_FILES)
|
||||
return model_cached and codec_cached
|
||||
|
||||
async def load_model(self, model_size: str = "1B") -> None:
|
||||
"""Load the TADA model and encoder."""
|
||||
if self.model is not None and self.model_size == model_size:
|
||||
return
|
||||
async with self._model_load_lock:
|
||||
if self.model is not None and self.model_size == model_size:
|
||||
return
|
||||
# Unload existing model if switching sizes
|
||||
if self.model is not None:
|
||||
self.unload_model()
|
||||
self.model_size = model_size
|
||||
await asyncio.to_thread(self._load_model_sync, model_size)
|
||||
|
||||
def _load_model_sync(self, model_size: str = "1B"):
|
||||
"""Synchronous model loading with progress tracking."""
|
||||
model_name = f"tada-{model_size.lower()}"
|
||||
is_cached = self._is_model_cached(model_size)
|
||||
repo = TADA_MODEL_REPOS.get(model_size, TADA_1B_REPO)
|
||||
|
||||
with model_load_progress(model_name, is_cached):
|
||||
import torch
|
||||
from huggingface_hub import snapshot_download
|
||||
|
||||
device = self._get_device()
|
||||
self._device = device
|
||||
logger.info(f"Loading HumeAI TADA {model_size} on {device}...")
|
||||
|
||||
# Download codec (encoder + decoder) if not cached
|
||||
logger.info("Downloading TADA codec...")
|
||||
snapshot_download(
|
||||
repo_id=TADA_CODEC_REPO,
|
||||
token=None,
|
||||
allow_patterns=["*.safetensors", "*.json", "*.txt", "*.bin"],
|
||||
)
|
||||
|
||||
# Download model weights if not cached
|
||||
logger.info(f"Downloading TADA {model_size} model...")
|
||||
snapshot_download(
|
||||
repo_id=repo,
|
||||
token=None,
|
||||
allow_patterns=["*.safetensors", "*.json", "*.txt", "*.bin", "*.model"],
|
||||
)
|
||||
|
||||
# Determine dtype — use bf16 on CUDA for ~50% memory savings
|
||||
if device == "cuda" and torch.cuda.is_bf16_supported():
|
||||
model_dtype = torch.bfloat16
|
||||
else:
|
||||
model_dtype = torch.float32
|
||||
|
||||
# Load encoder (only needed for voice prompt encoding)
|
||||
from tada.modules.encoder import Encoder
|
||||
logger.info("Loading TADA encoder...")
|
||||
self.encoder = Encoder.from_pretrained(
|
||||
TADA_CODEC_REPO, subfolder="encoder"
|
||||
).to(device)
|
||||
self.encoder.eval()
|
||||
|
||||
# Load the causal LM (includes decoder for wav generation)
|
||||
from tada.modules.tada import TadaForCausalLM
|
||||
logger.info(f"Loading TADA {model_size} model...")
|
||||
self.model = TadaForCausalLM.from_pretrained(
|
||||
repo, torch_dtype=model_dtype
|
||||
).to(device)
|
||||
self.model.eval()
|
||||
|
||||
logger.info(f"HumeAI TADA {model_size} loaded successfully on {device}")
|
||||
|
||||
def unload_model(self) -> None:
|
||||
"""Unload model and encoder to free memory."""
|
||||
if self.model is not None:
|
||||
del self.model
|
||||
self.model = None
|
||||
if self.encoder is not None:
|
||||
del self.encoder
|
||||
self.encoder = None
|
||||
|
||||
self._device = None
|
||||
|
||||
import torch
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
|
||||
logger.info("HumeAI TADA unloaded")
|
||||
|
||||
async def create_voice_prompt(
|
||||
self,
|
||||
audio_path: str,
|
||||
reference_text: str,
|
||||
use_cache: bool = True,
|
||||
) -> Tuple[dict, bool]:
|
||||
"""
|
||||
Create voice prompt from reference audio using TADA's encoder.
|
||||
|
||||
TADA's encoder performs forced alignment between audio and text tokens,
|
||||
producing an EncoderOutput with 1:1 token-audio alignment. If no
|
||||
reference_text is provided, the encoder uses built-in ASR (English only).
|
||||
|
||||
We serialize the EncoderOutput to a dict for caching.
|
||||
"""
|
||||
await self.load_model(self.model_size)
|
||||
|
||||
cache_key = (
|
||||
"tada_" + get_cache_key(audio_path, reference_text)
|
||||
) if use_cache else None
|
||||
|
||||
if cache_key:
|
||||
cached = get_cached_voice_prompt(cache_key)
|
||||
if cached is not None and isinstance(cached, dict):
|
||||
return cached, True
|
||||
|
||||
def _encode_sync():
|
||||
import torch
|
||||
import torchaudio
|
||||
|
||||
device = self._device
|
||||
|
||||
# Load and prepare audio
|
||||
audio, sr = torchaudio.load(str(audio_path))
|
||||
audio = audio.to(device)
|
||||
|
||||
# Encode with forced alignment
|
||||
text_arg = [reference_text] if reference_text else None
|
||||
prompt = self.encoder(
|
||||
audio, text=text_arg, sample_rate=sr
|
||||
)
|
||||
|
||||
# Serialize EncoderOutput to a dict of CPU tensors for caching
|
||||
prompt_dict = {}
|
||||
for field_name in prompt.__dataclass_fields__:
|
||||
val = getattr(prompt, field_name)
|
||||
if isinstance(val, torch.Tensor):
|
||||
prompt_dict[field_name] = val.detach().cpu()
|
||||
elif isinstance(val, list):
|
||||
prompt_dict[field_name] = val
|
||||
elif isinstance(val, (int, float)):
|
||||
prompt_dict[field_name] = val
|
||||
else:
|
||||
prompt_dict[field_name] = val
|
||||
return prompt_dict
|
||||
|
||||
encoded = await asyncio.to_thread(_encode_sync)
|
||||
|
||||
if cache_key:
|
||||
cache_voice_prompt(cache_key, encoded)
|
||||
|
||||
return encoded, False
|
||||
|
||||
async def combine_voice_prompts(
|
||||
self,
|
||||
audio_paths: List[str],
|
||||
reference_texts: List[str],
|
||||
) -> Tuple[np.ndarray, str]:
|
||||
return await _combine_voice_prompts(audio_paths, reference_texts, sample_rate=24000)
|
||||
|
||||
async def generate(
|
||||
self,
|
||||
text: str,
|
||||
voice_prompt: dict,
|
||||
language: str = "en",
|
||||
seed: Optional[int] = None,
|
||||
instruct: Optional[str] = None,
|
||||
) -> Tuple[np.ndarray, int]:
|
||||
"""
|
||||
Generate audio from text using HumeAI TADA.
|
||||
|
||||
Args:
|
||||
text: Text to synthesize
|
||||
voice_prompt: Serialized EncoderOutput dict from create_voice_prompt()
|
||||
language: Language code (en, ar, de, es, fr, it, ja, pl, pt, zh)
|
||||
seed: Random seed for reproducibility
|
||||
instruct: Not supported by TADA (ignored)
|
||||
|
||||
Returns:
|
||||
Tuple of (audio_array, sample_rate=24000)
|
||||
"""
|
||||
await self.load_model(self.model_size)
|
||||
|
||||
def _generate_sync():
|
||||
import torch
|
||||
from tada.modules.encoder import EncoderOutput
|
||||
|
||||
if seed is not None:
|
||||
torch.manual_seed(seed)
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.manual_seed(seed)
|
||||
|
||||
device = self._device
|
||||
|
||||
# Reconstruct EncoderOutput from the cached dict
|
||||
restored = {}
|
||||
for k, v in voice_prompt.items():
|
||||
if isinstance(v, torch.Tensor):
|
||||
# Move to device and match model dtype for float tensors
|
||||
if v.is_floating_point():
|
||||
model_dtype = next(self.model.parameters()).dtype
|
||||
restored[k] = v.to(device=device, dtype=model_dtype)
|
||||
else:
|
||||
restored[k] = v.to(device=device)
|
||||
else:
|
||||
restored[k] = v
|
||||
|
||||
prompt = EncoderOutput(**restored)
|
||||
|
||||
# For non-English with the 3B-ML model, we could reload the
|
||||
# encoder with the language-specific aligner. However, the
|
||||
# generation itself is language-agnostic — only the encoder's
|
||||
# aligner changes. Since we encode at create_voice_prompt time,
|
||||
# the language is already baked in. For simplicity, we don't
|
||||
# reload the encoder here.
|
||||
|
||||
logger.info(f"[TADA] Generating ({language}), text length: {len(text)}")
|
||||
|
||||
output = self.model.generate(
|
||||
prompt=prompt,
|
||||
text=text,
|
||||
)
|
||||
|
||||
# output.audio is a list of tensors (one per batch item)
|
||||
if output.audio and output.audio[0] is not None:
|
||||
audio_tensor = output.audio[0]
|
||||
audio = audio_tensor.detach().cpu().numpy().squeeze().astype(np.float32)
|
||||
else:
|
||||
logger.warning("[TADA] Generation produced no audio")
|
||||
audio = np.zeros(24000, dtype=np.float32)
|
||||
|
||||
return audio, 24000
|
||||
|
||||
return await asyncio.to_thread(_generate_sync)
|
||||
@@ -186,6 +186,50 @@ def build_server(cuda=False):
|
||||
# needed by LuxTTS for text-to-phoneme conversion
|
||||
"--collect-all",
|
||||
"piper_phonemize",
|
||||
# HumeAI TADA — speech-language model using Llama + flow matching
|
||||
"--hidden-import",
|
||||
"backend.backends.hume_backend",
|
||||
"--hidden-import",
|
||||
"tada",
|
||||
"--hidden-import",
|
||||
"tada.modules",
|
||||
"--hidden-import",
|
||||
"tada.modules.tada",
|
||||
"--hidden-import",
|
||||
"tada.modules.encoder",
|
||||
"--hidden-import",
|
||||
"tada.modules.decoder",
|
||||
"--hidden-import",
|
||||
"tada.modules.aligner",
|
||||
"--hidden-import",
|
||||
"tada.modules.acoustic_spkr_verf",
|
||||
"--hidden-import",
|
||||
"tada.nn",
|
||||
"--hidden-import",
|
||||
"tada.nn.vibevoice",
|
||||
"--hidden-import",
|
||||
"tada.utils",
|
||||
"--hidden-import",
|
||||
"tada.utils.gray_code",
|
||||
"--hidden-import",
|
||||
"tada.utils.text",
|
||||
# descript-audio-codec (DAC) — used by TADA for Snake1d layers
|
||||
"--hidden-import",
|
||||
"dac",
|
||||
"--hidden-import",
|
||||
"dac.nn",
|
||||
"--hidden-import",
|
||||
"dac.nn.layers",
|
||||
"--hidden-import",
|
||||
"dac.model",
|
||||
"--hidden-import",
|
||||
"dac.model.dac",
|
||||
"--collect-all",
|
||||
"dac",
|
||||
"--hidden-import",
|
||||
"torchaudio",
|
||||
"--collect-submodules",
|
||||
"tada",
|
||||
]
|
||||
)
|
||||
|
||||
|
||||
+2
-2
@@ -66,9 +66,9 @@ class GenerationRequest(BaseModel):
|
||||
text: str = Field(..., min_length=1, max_length=50000)
|
||||
language: str = Field(default="en", pattern="^(zh|en|ja|ko|de|fr|ru|pt|es|it|he|ar|da|el|fi|hi|ms|nl|no|pl|sv|sw|tr)$")
|
||||
seed: Optional[int] = Field(None, ge=0)
|
||||
model_size: Optional[str] = Field(default="1.7B", pattern="^(1\\.7B|0\\.6B)$")
|
||||
model_size: Optional[str] = Field(default="1.7B", pattern="^(1\\.7B|0\\.6B|1B|3B)$")
|
||||
instruct: Optional[str] = Field(None, max_length=500)
|
||||
engine: Optional[str] = Field(default="qwen", pattern="^(qwen|luxtts|chatterbox|chatterbox_turbo)$")
|
||||
engine: Optional[str] = Field(default="qwen", pattern="^(qwen|luxtts|chatterbox|chatterbox_turbo|tada)$")
|
||||
max_chunk_chars: int = Field(
|
||||
default=800, ge=100, le=5000, description="Max characters per chunk for long text splitting"
|
||||
)
|
||||
|
||||
@@ -33,6 +33,11 @@ s3tokenizer
|
||||
spacy-pkuseg
|
||||
pyloudnorm
|
||||
|
||||
# HumeAI TADA sub-dependencies (hume-tada itself is installed
|
||||
# --no-deps in the setup script because it pins torch>=2.7,<2.8)
|
||||
descript-audio-codec>=1.0.0
|
||||
torchaudio
|
||||
|
||||
# Audio processing
|
||||
librosa>=0.10.0
|
||||
soundfile>=0.12.0
|
||||
|
||||
@@ -46,6 +46,8 @@ setup-python:
|
||||
{{ pip }} install -r {{ backend_dir }}/requirements.txt
|
||||
# Chatterbox pins numpy<1.26 / torch==2.6 which break on Python 3.12+
|
||||
{{ pip }} install --no-deps chatterbox-tts
|
||||
# HumeAI TADA pins torch>=2.7,<2.8 which conflicts with our torch>=2.1
|
||||
{{ pip }} install --no-deps hume-tada
|
||||
# Apple Silicon: install MLX backend
|
||||
if [ "$(uname -m)" = "arm64" ] && [ "$(uname)" = "Darwin" ]; then
|
||||
echo "Detected Apple Silicon — installing MLX dependencies..."
|
||||
@@ -74,6 +76,7 @@ setup-python:
|
||||
}
|
||||
& "{{ pip }}" install -r {{ backend_dir }}/requirements.txt
|
||||
& "{{ pip }}" install --no-deps chatterbox-tts
|
||||
& "{{ pip }}" install --no-deps hume-tada
|
||||
& "{{ pip }}" install git+https://github.com/QwenLM/Qwen3-TTS.git
|
||||
& "{{ pip }}" install pyinstaller ruff pytest pytest-asyncio -q
|
||||
Write-Host "Python environment ready."
|
||||
|
||||
Reference in New Issue
Block a user