Skip to content

The open-source AI voice studio. Clone, dictate, create.

fix: download progress tracking for all engines and inline progress UI

James Pinecc07d4d3c91f
diff --git a/app/src/components/ServerSettings/GpuAcceleration.tsx b/app/src/components/ServerSettings/GpuAcceleration.tsx
index 17da7690..69824d63 100644
--- a/app/src/components/ServerSettings/GpuAcceleration.tsx
+++ b/app/src/components/ServerSettings/GpuAcceleration.tsx
@@ -32,7 +32,7 @@ export function GpuAcceleration() {
} = useQuery({
queryKey: ['cuda-status', serverUrl],
queryFn: () => apiClient.getCudaStatus(),
- refetchInterval: cudaStatusLoading ? false : 10000,
+ refetchInterval: (query) => (query.state.status === 'pending' ? false : 10000),
retry: 1,
enabled: !!health, // Only fetch when backend is reachable
});
diff --git a/app/src/components/ServerSettings/ModelManagement.tsx b/app/src/components/ServerSettings/ModelManagement.tsx
index 4783a880..ec94cb12 100644
--- a/app/src/components/ServerSettings/ModelManagement.tsx
+++ b/app/src/components/ServerSettings/ModelManagement.tsx
@@ -16,7 +16,7 @@ import {
X,
Zap,
} from 'lucide-react';
-import { useCallback, useState } from 'react';
+import { useCallback, useMemo, useState } from 'react';
import {
AlertDialog,
AlertDialogAction,
@@ -36,6 +36,7 @@ import {
DialogHeader,
DialogTitle,
} from '@/components/ui/dialog';
+import { Progress } from '@/components/ui/progress';
import { useToast } from '@/components/ui/use-toast';
import { apiClient } from '@/lib/api/client';
import type { ActiveDownloadTask, HuggingFaceModelInfo, ModelStatus } from '@/lib/api/types';
@@ -73,6 +74,14 @@ function formatPipelineTag(tag: string): string {
.join(' ');
}
+function formatBytes(bytes: number): string {
+ if (bytes === 0) return '0 B';
+ const k = 1024;
+ const sizes = ['B', 'KB', 'MB', 'GB'];
+ const i = Math.floor(Math.log(bytes) / Math.log(k));
+ return `${(bytes / k ** i).toFixed(1)} ${sizes[i]}`;
+}
+
export function ModelManagement() {
const { toast } = useToast();
const queryClient = useQueryClient();
@@ -98,7 +107,11 @@ export function ModelManagement() {
const { data: activeTasks } = useQuery({
queryKey: ['activeTasks'],
queryFn: () => apiClient.getActiveTasks(),
- refetchInterval: 5000,
+ refetchInterval: (query) => {
+ const data = query.state.data;
+ const hasActive = data?.downloads.some((d) => d.status === 'downloading');
+ return hasActive ? 1000 : 5000;
+ },
});
// HuggingFace model card query - only fetches when modal is open and model has a repo ID
@@ -133,6 +146,19 @@ export function ModelManagement() {
const errorCount = erroredDownloads.size;
+ // Build progress map from active tasks for inline display
+ const downloadProgressMap = useMemo(() => {
+ const map = new Map<string, ActiveDownloadTask>();
+ if (activeTasks?.downloads) {
+ for (const dl of activeTasks.downloads) {
+ if (dl.status === 'downloading') {
+ map.set(dl.model_name, dl);
+ }
+ }
+ }
+ return map;
+ }, [activeTasks]);
+
const handleDownloadComplete = useCallback(() => {
setDownloadingModel(null);
setDownloadingDisplayName(null);
@@ -371,16 +397,29 @@ export function ModelManagement() {
)}
</div>
- {/* Name + meta */}
+ {/* Name + inline progress */}
<div className="flex-1 min-w-0">
<span className="text-sm font-medium">{model.display_name}</span>
+ {isDownloading &&
+ (() => {
+ const dl = downloadProgressMap.get(model.model_name);
+ const pct = dl?.progress ?? 0;
+ const hasProgress = dl && dl.total && dl.total > 0;
+ return (
+ <div className="mt-1 space-y-0.5">
+ <Progress value={hasProgress ? pct : undefined} className="h-1" />
+ <div className="text-[10px] text-muted-foreground truncate">
+ {hasProgress
+ ? `${formatBytes(dl.current ?? 0)} / ${formatBytes(dl.total!)} (${pct.toFixed(0)}%)`
+ : dl?.filename || 'Connecting...'}
+ </div>
+ </div>
+ );
+ })()}
</div>
{/* Right side info */}
<div className="shrink-0 flex items-center gap-2">
- {isDownloading && (
- <span className="text-xs text-muted-foreground">Downloading...</span>
- )}
{hasError && (
<Badge variant="destructive" className="text-[10px] h-5">
Error
@@ -510,12 +549,6 @@ export function ModelManagement() {
Downloaded
</Badge>
)}
- {selectedState?.isDownloading && (
- <Badge variant="outline" className="text-xs">
- <Loader2 className="h-3 w-3 mr-1 animate-spin" />
- Downloading
- </Badge>
- )}
{selectedState?.hasError && (
<Badge variant="destructive" className="text-xs">
<CircleX className="h-3 w-3 mr-1" />
@@ -633,10 +666,25 @@ export function ModelManagement() {
</>
) : selectedState?.isDownloading ? (
<>
- <Button size="sm" variant="outline" disabled className="flex-1">
- <Loader2 className="h-4 w-4 mr-2 animate-spin" />
- Downloading...
- </Button>
+ <div className="flex-1 space-y-2">
+ {(() => {
+ const dl = freshSelectedModel
+ ? downloadProgressMap.get(freshSelectedModel.model_name)
+ : undefined;
+ const pct = dl?.progress ?? 0;
+ const hasProgress = dl && dl.total && dl.total > 0;
+ return (
+ <>
+ <Progress value={hasProgress ? pct : undefined} className="h-2" />
+ <div className="text-xs text-muted-foreground">
+ {hasProgress
+ ? `${formatBytes(dl.current ?? 0)} / ${formatBytes(dl.total!)} (${pct.toFixed(1)}%)`
+ : dl?.filename || 'Connecting to HuggingFace...'}
+ </div>
+ </>
+ );
+ })()}
+ </div>
<Button
size="sm"
onClick={() => handleCancel(freshSelectedModel.model_name)}
diff --git a/app/src/lib/api/types.ts b/app/src/lib/api/types.ts
index 0da89da5..9819e00a 100644
--- a/app/src/lib/api/types.ts
+++ b/app/src/lib/api/types.ts
@@ -155,6 +155,10 @@ export interface ActiveDownloadTask {
status: string;
started_at: string;
error?: string;
+ progress?: number; // 0-100 percentage
+ current?: number; // bytes downloaded
+ total?: number; // total bytes
+ filename?: string; // current file being downloaded
}
export interface ActiveGenerationTask {
diff --git a/backend/backends/chatterbox_backend.py b/backend/backends/chatterbox_backend.py
index 9078f686..88f87d4e 100644
--- a/backend/backends/chatterbox_backend.py
+++ b/backend/backends/chatterbox_backend.py
@@ -103,19 +103,27 @@ class ChatterboxTTSBackend:
def _load_model_sync(self):
"""Synchronous model loading."""
+ from ..utils.hf_progress import HFProgressTracker, create_hf_progress_callback
+
progress_manager = get_progress_manager()
task_manager = get_task_manager()
model_name = "chatterbox-tts"
is_cached = self._is_model_cached()
+ # Set up HF progress tracking (intercepts tqdm for file-level progress)
+ progress_callback = create_hf_progress_callback(model_name, progress_manager)
+ tracker = HFProgressTracker(progress_callback, filter_non_downloads=is_cached)
+ tracker_context = tracker.patch_download()
+ tracker_context.__enter__()
+
if not is_cached:
task_manager.start_download(model_name)
progress_manager.update_progress(
model_name=model_name,
current=0,
total=0,
- filename="Downloading Chatterbox model...",
+ filename="Connecting to HuggingFace...",
status="downloading",
)
@@ -131,25 +139,28 @@ class ChatterboxTTSBackend:
# Monkey-patch torch.load for CPU loading. The model's .pt files
# were saved on CUDA; from_pretrained() doesn't pass map_location
# so loading on CPU fails without this.
- if device == "cpu":
- _orig_torch_load = torch.load
-
- def _patched_load(*args, **kwargs):
- kwargs.setdefault("map_location", "cpu")
- return _orig_torch_load(*args, **kwargs)
-
- with ChatterboxTTSBackend._load_lock:
- torch.load = _patched_load
- try:
- self.model = ChatterboxMultilingualTTS.from_pretrained(
- device=device,
- )
- finally:
- torch.load = _orig_torch_load
- else:
- self.model = ChatterboxMultilingualTTS.from_pretrained(
- device=device,
- )
+ try:
+ if device == "cpu":
+ _orig_torch_load = torch.load
+
+ def _patched_load(*args, **kwargs):
+ kwargs.setdefault("map_location", "cpu")
+ return _orig_torch_load(*args, **kwargs)
+
+ with ChatterboxTTSBackend._load_lock:
+ torch.load = _patched_load
+ try:
+ self.model = ChatterboxMultilingualTTS.from_pretrained(
+ device=device,
+ )
+ finally:
+ torch.load = _orig_torch_load
+ else:
+ self.model = ChatterboxMultilingualTTS.from_pretrained(
+ device=device,
+ )
+ finally:
+ tracker_context.__exit__(None, None, None)
# Fix: transformers >= 4.36 defaults LlamaModel to sdpa attention
# which doesn't support output_attentions=True (needed by
diff --git a/backend/backends/luxtts_backend.py b/backend/backends/luxtts_backend.py
index 7e692139..549e44ff 100644
--- a/backend/backends/luxtts_backend.py
+++ b/backend/backends/luxtts_backend.py
@@ -94,19 +94,27 @@ class LuxTTSBackend:
def _load_model_sync(self):
"""Synchronous model loading."""
+ from ..utils.hf_progress import HFProgressTracker, create_hf_progress_callback
+
progress_manager = get_progress_manager()
task_manager = get_task_manager()
model_name = "luxtts"
is_cached = self._is_model_cached()
+ # Set up HF progress tracking (intercepts tqdm for file-level progress)
+ progress_callback = create_hf_progress_callback(model_name, progress_manager)
+ tracker = HFProgressTracker(progress_callback, filter_non_downloads=is_cached)
+ tracker_context = tracker.patch_download()
+ tracker_context.__enter__()
+
if not is_cached:
task_manager.start_download(model_name)
progress_manager.update_progress(
model_name=model_name,
current=0,
total=0,
- filename="Downloading LuxTTS model...",
+ filename="Connecting to HuggingFace...",
status="downloading",
)
@@ -117,19 +125,22 @@ class LuxTTSBackend:
logger.info(f"Loading LuxTTS on {device}...")
# LuxTTS constructor downloads model and loads everything
- if device == "cpu":
- import os
- threads = os.cpu_count() or 4
- self.model = LuxTTS(
- model_path=LUXTTS_HF_REPO,
- device="cpu",
- threads=min(threads, 8),
- )
- else:
- self.model = LuxTTS(
- model_path=LUXTTS_HF_REPO,
- device=device,
- )
+ try:
+ if device == "cpu":
+ import os
+ threads = os.cpu_count() or 4
+ self.model = LuxTTS(
+ model_path=LUXTTS_HF_REPO,
+ device="cpu",
+ threads=min(threads, 8),
+ )
+ else:
+ self.model = LuxTTS(
+ model_path=LUXTTS_HF_REPO,
+ device=device,
+ )
+ finally:
+ tracker_context.__exit__(None, None, None)
if not is_cached:
progress_manager.mark_complete(model_name)
diff --git a/backend/main.py b/backend/main.py
index 7eeabe40..3d2ec359 100644
--- a/backend/main.py
+++ b/backend/main.py
@@ -1912,11 +1912,22 @@ async def get_active_tasks():
pm_data = progress_manager._progress.get(model_name)
if pm_data:
error = pm_data.get("error")
+ # Include progress data if available
+ prog = progress or {}
+ if not prog:
+ with progress_manager._lock:
+ pm_data = progress_manager._progress.get(model_name)
+ if pm_data:
+ prog = pm_data
active_downloads.append(models.ActiveDownloadTask(
model_name=model_name,
status=task.status,
started_at=task.started_at,
error=error,
+ progress=prog.get("progress"),
+ current=prog.get("current"),
+ total=prog.get("total"),
+ filename=prog.get("filename"),
))
elif progress:
# Progress exists but no task - create from progress data
@@ -1934,6 +1945,10 @@ async def get_active_tasks():
status=progress.get("status", "downloading"),
started_at=started_at,
error=progress.get("error"),
+ progress=progress.get("progress"),
+ current=progress.get("current"),
+ total=progress.get("total"),
+ filename=progress.get("filename"),
))
# Get active generations
diff --git a/backend/models.py b/backend/models.py
index 9b945adb..c46ded58 100644
--- a/backend/models.py
+++ b/backend/models.py
@@ -158,6 +158,10 @@ class ActiveDownloadTask(BaseModel):
status: str
started_at: datetime
error: Optional[str] = None
+ progress: Optional[float] = None # 0-100 percentage
+ current: Optional[int] = None # bytes downloaded
+ total: Optional[int] = None # total bytes
+ filename: Optional[str] = None # current file being downloaded
class ActiveGenerationTask(BaseModel):