- Add diarize.download IPC handler that downloads the pyannote model and returns user-friendly error messages (missing license, bad token) - Add download_diarize_model Tauri command - Add "Test & Download Model" button in Speakers settings tab - Update instructions to list both required model licenses (speaker-diarization-3.1 AND segmentation-3.0) - Make all HuggingFace URLs clickable (opens in system browser) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
432 lines
13 KiB
Svelte
432 lines
13 KiB
Svelte
<script lang="ts">
|
|
import { invoke } from '@tauri-apps/api/core';
|
|
import { openUrl } from '@tauri-apps/plugin-opener';
|
|
import { settings, saveSettings, type AppSettings } from '$lib/stores/settings';
|
|
|
|
interface Props {
|
|
visible: boolean;
|
|
onClose: () => void;
|
|
}
|
|
|
|
let { visible, onClose }: Props = $props();
|
|
|
|
let localSettings = $state<AppSettings>({ ...$settings });
|
|
let activeTab = $state<'transcription' | 'speakers' | 'ai' | 'local'>('transcription');
|
|
let modelStatus = $state<'idle' | 'downloading' | 'success' | 'error'>('idle');
|
|
let modelError = $state('');
|
|
|
|
async function testAndDownloadModel() {
|
|
if (!localSettings.hf_token) {
|
|
modelStatus = 'error';
|
|
modelError = 'Please enter a HuggingFace token first.';
|
|
return;
|
|
}
|
|
modelStatus = 'downloading';
|
|
modelError = '';
|
|
try {
|
|
const result = await invoke<{ ok: boolean; error?: string }>('download_diarize_model', {
|
|
hfToken: localSettings.hf_token,
|
|
});
|
|
if (result.ok) {
|
|
modelStatus = 'success';
|
|
} else {
|
|
modelStatus = 'error';
|
|
modelError = result.error || 'Unknown error';
|
|
}
|
|
} catch (err) {
|
|
modelStatus = 'error';
|
|
modelError = String(err);
|
|
}
|
|
}
|
|
|
|
// Sync when settings store changes
|
|
$effect(() => {
|
|
localSettings = { ...$settings };
|
|
});
|
|
|
|
async function handleSave() {
|
|
await saveSettings(localSettings);
|
|
onClose();
|
|
}
|
|
|
|
function handleCancel() {
|
|
localSettings = { ...$settings };
|
|
onClose();
|
|
}
|
|
|
|
function handleOverlayClick(e: MouseEvent) {
|
|
if ((e.target as HTMLElement).classList.contains('modal-overlay')) {
|
|
handleCancel();
|
|
}
|
|
}
|
|
</script>
|
|
|
|
{#if visible}
|
|
<!-- svelte-ignore a11y_no_static_element_interactions -->
|
|
<div class="modal-overlay" onclick={handleOverlayClick} onkeydown={(e) => { if (e.key === 'Escape') handleCancel(); }}>
|
|
<div class="modal">
|
|
<div class="modal-header">
|
|
<h2>Settings</h2>
|
|
<button class="close-btn" onclick={handleCancel}>x</button>
|
|
</div>
|
|
|
|
<div class="tabs">
|
|
<button class="tab" class:active={activeTab === 'transcription'} onclick={() => activeTab = 'transcription'}>
|
|
Transcription
|
|
</button>
|
|
<button class="tab" class:active={activeTab === 'speakers'} onclick={() => activeTab = 'speakers'}>
|
|
Speakers
|
|
</button>
|
|
<button class="tab" class:active={activeTab === 'ai'} onclick={() => activeTab = 'ai'}>
|
|
AI Provider
|
|
</button>
|
|
<button class="tab" class:active={activeTab === 'local'} onclick={() => activeTab = 'local'}>
|
|
Local AI
|
|
</button>
|
|
</div>
|
|
|
|
<div class="modal-body">
|
|
{#if activeTab === 'transcription'}
|
|
<div class="field">
|
|
<label for="stt-model">Whisper Model</label>
|
|
<select id="stt-model" bind:value={localSettings.transcription_model}>
|
|
<option value="tiny">Tiny (fastest, least accurate)</option>
|
|
<option value="base">Base (fast, good accuracy)</option>
|
|
<option value="small">Small (balanced)</option>
|
|
<option value="medium">Medium (slower, better accuracy)</option>
|
|
<option value="large-v3">Large v3 (slowest, best accuracy)</option>
|
|
</select>
|
|
</div>
|
|
<div class="field">
|
|
<label for="stt-device">Device</label>
|
|
<select id="stt-device" bind:value={localSettings.transcription_device}>
|
|
<option value="cpu">CPU</option>
|
|
<option value="cuda">CUDA (NVIDIA GPU)</option>
|
|
</select>
|
|
</div>
|
|
<div class="field">
|
|
<label for="stt-lang">Language (blank = auto-detect)</label>
|
|
<input id="stt-lang" type="text" bind:value={localSettings.transcription_language} placeholder="e.g., en, es, fr" />
|
|
</div>
|
|
{:else if activeTab === 'speakers'}
|
|
<div class="field">
|
|
<label for="hf-token">HuggingFace Token</label>
|
|
<input id="hf-token" type="password" bind:value={localSettings.hf_token} placeholder="hf_..." />
|
|
</div>
|
|
<div class="info-box">
|
|
<p class="info-title">Setup (one-time)</p>
|
|
<p>Speaker detection uses <strong>pyannote.audio</strong> models hosted on HuggingFace. You must accept the license for each model:</p>
|
|
<ol>
|
|
<li>Create a free account at <!-- svelte-ignore a11y_no_static_element_interactions --><a class="ext-link" onclick={() => openUrl('https://huggingface.co/join')}>huggingface.co</a></li>
|
|
<li>Accept the license on <strong>each</strong> of these pages:
|
|
<ul>
|
|
<!-- svelte-ignore a11y_no_static_element_interactions -->
|
|
<li><a class="ext-link" onclick={() => openUrl('https://huggingface.co/pyannote/speaker-diarization-3.1')}>pyannote/speaker-diarization-3.1</a></li>
|
|
<!-- svelte-ignore a11y_no_static_element_interactions -->
|
|
<li><a class="ext-link" onclick={() => openUrl('https://huggingface.co/pyannote/segmentation-3.0')}>pyannote/segmentation-3.0</a></li>
|
|
</ul>
|
|
</li>
|
|
<!-- svelte-ignore a11y_no_static_element_interactions -->
|
|
<li>Create a token at <a class="ext-link" onclick={() => openUrl('https://huggingface.co/settings/tokens')}>huggingface.co/settings/tokens</a> (read access)</li>
|
|
<li>Paste the token above and click <strong>Test & Download</strong></li>
|
|
</ol>
|
|
</div>
|
|
<button
|
|
class="btn-download"
|
|
onclick={testAndDownloadModel}
|
|
disabled={modelStatus === 'downloading'}
|
|
>
|
|
{#if modelStatus === 'downloading'}
|
|
Downloading model...
|
|
{:else}
|
|
Test & Download Model
|
|
{/if}
|
|
</button>
|
|
{#if modelStatus === 'success'}
|
|
<p class="status-success">Model downloaded successfully. Speaker detection is ready.</p>
|
|
{/if}
|
|
{#if modelStatus === 'error'}
|
|
<p class="status-error">{modelError}</p>
|
|
{/if}
|
|
<div class="field checkbox" style="margin-top: 1rem;">
|
|
<label>
|
|
<input type="checkbox" bind:checked={localSettings.skip_diarization} />
|
|
Skip speaker detection (faster, no speaker labels)
|
|
</label>
|
|
</div>
|
|
{:else if activeTab === 'ai'}
|
|
<div class="field">
|
|
<label for="ai-provider">AI Provider</label>
|
|
<select id="ai-provider" bind:value={localSettings.ai_provider}>
|
|
<option value="local">Local (llama-server)</option>
|
|
<option value="openai">OpenAI</option>
|
|
<option value="anthropic">Anthropic</option>
|
|
<option value="litellm">LiteLLM</option>
|
|
</select>
|
|
</div>
|
|
|
|
{#if localSettings.ai_provider === 'openai'}
|
|
<div class="field">
|
|
<label for="openai-key">OpenAI API Key</label>
|
|
<input id="openai-key" type="password" bind:value={localSettings.openai_api_key} placeholder="sk-..." />
|
|
</div>
|
|
<div class="field">
|
|
<label for="openai-model">Model</label>
|
|
<input id="openai-model" type="text" bind:value={localSettings.openai_model} />
|
|
</div>
|
|
{:else if localSettings.ai_provider === 'anthropic'}
|
|
<div class="field">
|
|
<label for="anthropic-key">Anthropic API Key</label>
|
|
<input id="anthropic-key" type="password" bind:value={localSettings.anthropic_api_key} placeholder="sk-ant-..." />
|
|
</div>
|
|
<div class="field">
|
|
<label for="anthropic-model">Model</label>
|
|
<input id="anthropic-model" type="text" bind:value={localSettings.anthropic_model} />
|
|
</div>
|
|
{:else if localSettings.ai_provider === 'litellm'}
|
|
<div class="field">
|
|
<label for="litellm-model">Model</label>
|
|
<input id="litellm-model" type="text" bind:value={localSettings.litellm_model} placeholder="provider/model-name" />
|
|
</div>
|
|
{/if}
|
|
{:else}
|
|
<div class="field">
|
|
<label for="llama-binary">llama-server Binary Path</label>
|
|
<input id="llama-binary" type="text" bind:value={localSettings.local_binary_path} placeholder="llama-server" />
|
|
</div>
|
|
<div class="field">
|
|
<label for="llama-model">GGUF Model Path</label>
|
|
<input id="llama-model" type="text" bind:value={localSettings.local_model_path} placeholder="~/.voicetonotes/models/model.gguf" />
|
|
</div>
|
|
<p class="hint">
|
|
Place GGUF model files in ~/.voicetonotes/models/ for auto-detection.
|
|
The local AI server uses the OpenAI-compatible API from llama.cpp.
|
|
</p>
|
|
{/if}
|
|
</div>
|
|
|
|
<div class="modal-footer">
|
|
<button class="btn-secondary" onclick={handleCancel}>Cancel</button>
|
|
<button class="btn-primary" onclick={handleSave}>Save</button>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
{/if}
|
|
|
|
<style>
|
|
.modal-overlay {
|
|
position: fixed;
|
|
inset: 0;
|
|
background: rgba(0, 0, 0, 0.6);
|
|
display: flex;
|
|
align-items: center;
|
|
justify-content: center;
|
|
z-index: 100;
|
|
}
|
|
.modal {
|
|
background: #16213e;
|
|
border-radius: 12px;
|
|
width: 500px;
|
|
max-width: 90vw;
|
|
max-height: 80vh;
|
|
display: flex;
|
|
flex-direction: column;
|
|
color: #e0e0e0;
|
|
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.5);
|
|
}
|
|
.modal-header {
|
|
display: flex;
|
|
align-items: center;
|
|
justify-content: space-between;
|
|
padding: 1rem 1.25rem;
|
|
border-bottom: 1px solid #2a3a5e;
|
|
}
|
|
.modal-header h2 {
|
|
margin: 0;
|
|
font-size: 1.1rem;
|
|
}
|
|
.close-btn {
|
|
background: none;
|
|
border: none;
|
|
color: #999;
|
|
font-size: 1.2rem;
|
|
cursor: pointer;
|
|
padding: 0.25rem;
|
|
}
|
|
.close-btn:hover {
|
|
color: #e0e0e0;
|
|
}
|
|
.tabs {
|
|
display: flex;
|
|
border-bottom: 1px solid #2a3a5e;
|
|
padding: 0 1.25rem;
|
|
}
|
|
.tab {
|
|
background: none;
|
|
border: none;
|
|
color: #888;
|
|
padding: 0.6rem 1rem;
|
|
cursor: pointer;
|
|
font-size: 0.85rem;
|
|
border-bottom: 2px solid transparent;
|
|
}
|
|
.tab:hover {
|
|
color: #e0e0e0;
|
|
}
|
|
.tab.active {
|
|
color: #e94560;
|
|
border-bottom-color: #e94560;
|
|
}
|
|
.modal-body {
|
|
padding: 1.25rem;
|
|
overflow-y: auto;
|
|
flex: 1;
|
|
}
|
|
.field {
|
|
margin-bottom: 1rem;
|
|
}
|
|
.field label {
|
|
display: block;
|
|
font-size: 0.8rem;
|
|
color: #aaa;
|
|
margin-bottom: 0.3rem;
|
|
}
|
|
.field input,
|
|
.field select {
|
|
width: 100%;
|
|
background: #1a1a2e;
|
|
color: #e0e0e0;
|
|
border: 1px solid #4a5568;
|
|
border-radius: 4px;
|
|
padding: 0.5rem;
|
|
font-size: 0.85rem;
|
|
font-family: inherit;
|
|
box-sizing: border-box;
|
|
}
|
|
.field input:focus,
|
|
.field select:focus {
|
|
outline: none;
|
|
border-color: #e94560;
|
|
}
|
|
.field.checkbox label {
|
|
display: flex;
|
|
align-items: center;
|
|
gap: 0.5rem;
|
|
cursor: pointer;
|
|
color: #e0e0e0;
|
|
}
|
|
.field.checkbox input {
|
|
width: auto;
|
|
}
|
|
.hint {
|
|
font-size: 0.75rem;
|
|
color: #666;
|
|
line-height: 1.4;
|
|
}
|
|
.info-box {
|
|
background: rgba(233, 69, 96, 0.05);
|
|
border: 1px solid #2a3a5e;
|
|
border-radius: 6px;
|
|
padding: 0.75rem 1rem;
|
|
margin-bottom: 1rem;
|
|
font-size: 0.8rem;
|
|
color: #b0b0b0;
|
|
line-height: 1.5;
|
|
}
|
|
.info-box p {
|
|
margin: 0 0 0.5rem;
|
|
}
|
|
.info-box p:last-child {
|
|
margin-bottom: 0;
|
|
}
|
|
.info-box .info-title {
|
|
color: #e0e0e0;
|
|
font-weight: 600;
|
|
font-size: 0.8rem;
|
|
}
|
|
.info-box ol {
|
|
margin: 0.25rem 0 0.5rem;
|
|
padding-left: 1.25rem;
|
|
}
|
|
.info-box li {
|
|
margin-bottom: 0.25rem;
|
|
}
|
|
.info-box strong {
|
|
color: #e0e0e0;
|
|
}
|
|
.ext-link {
|
|
color: #e94560;
|
|
cursor: pointer;
|
|
text-decoration: underline;
|
|
}
|
|
.ext-link:hover {
|
|
color: #ff6b81;
|
|
}
|
|
.info-box ul {
|
|
margin: 0.25rem 0;
|
|
padding-left: 1.25rem;
|
|
}
|
|
.btn-download {
|
|
background: #0f3460;
|
|
border: 1px solid #4a5568;
|
|
color: #e0e0e0;
|
|
padding: 0.5rem 1rem;
|
|
border-radius: 6px;
|
|
cursor: pointer;
|
|
font-size: 0.85rem;
|
|
width: 100%;
|
|
margin-bottom: 0.5rem;
|
|
}
|
|
.btn-download:hover:not(:disabled) {
|
|
background: #1a4a7a;
|
|
border-color: #e94560;
|
|
}
|
|
.btn-download:disabled {
|
|
opacity: 0.6;
|
|
cursor: not-allowed;
|
|
}
|
|
.status-success {
|
|
color: #4ecdc4;
|
|
font-size: 0.8rem;
|
|
margin: 0.25rem 0;
|
|
}
|
|
.status-error {
|
|
color: #e94560;
|
|
font-size: 0.8rem;
|
|
margin: 0.25rem 0;
|
|
word-break: break-word;
|
|
}
|
|
.modal-footer {
|
|
display: flex;
|
|
justify-content: flex-end;
|
|
gap: 0.5rem;
|
|
padding: 1rem 1.25rem;
|
|
border-top: 1px solid #2a3a5e;
|
|
}
|
|
.btn-secondary {
|
|
background: none;
|
|
border: 1px solid #4a5568;
|
|
color: #e0e0e0;
|
|
padding: 0.5rem 1rem;
|
|
border-radius: 6px;
|
|
cursor: pointer;
|
|
font-size: 0.85rem;
|
|
}
|
|
.btn-secondary:hover {
|
|
background: rgba(255,255,255,0.05);
|
|
}
|
|
.btn-primary {
|
|
background: #e94560;
|
|
border: none;
|
|
color: white;
|
|
padding: 0.5rem 1rem;
|
|
border-radius: 6px;
|
|
cursor: pointer;
|
|
font-size: 0.85rem;
|
|
font-weight: 500;
|
|
}
|
|
.btn-primary:hover {
|
|
background: #d63851;
|
|
}
|
|
</style>
|