Spaces:
Sleeping
Sleeping
File size: 28,303 Bytes
98c0f96 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 | # Patch Visualization App - Simplified Design
**Purpose**: Interactive exploration of entropy-based patching strategies on pre-encoded audio
---
## Scope (Minimal)
### What We're Building
- Gradio app to explore **entropy-based patching only**
- Uses **10 pre-selected audio files** from `data/test-10/`
- Uses **single entropy model**: `archive/checkpoints/audio_peoplespeech_50k_scratch/best`
- **Precomputed data**: All entropy/perplexity computed offline
- **Focus**: Parameter exploration, not model inference
### What We're NOT Building
- β No audio upload
- β No model selection/switching
- β No other patching strategies (strided, space, BPE)
- β No export functionality
- β No batch processing
- β No comparison mode
---
## Data Pipeline
### Step 1: Precomputation Script
**Input**: 10 FLAC files from `data/test-10/`
**Process**:
1. Load audio with WavTokenizer
2. Encode to tokens (40 tok/sec, 4096 vocab)
3. Load entropy model from `archive/checkpoints/audio_peoplespeech_50k_scratch/best`
4. Compute entropy for each token position
5. Compute perplexity: `PPL(x_i) = 2^{H(x_i)}`
6. Generate spectrogram (for visualization)
7. Save to JSON
**Output**: `data/test-10/precomputed/<file_id>.json`
**JSON Schema**:
```json
{
"file_id": "1089-134691-0016",
"audio_path": "data/test-10/1089-134691-0016.flac",
"transcript": "...",
"audio_duration_sec": 7.23,
"sample_rate": 24000,
"tokens": [234, 1023, 892, ...], // WavTokenizer tokens
"entropies": [2.34, 1.89, 2.56, ...], // bits
"perplexities": [5.07, 3.71, 5.91, ...] // 2^entropy
}
```
**Note**: Spectrogram is computed at runtime from audio file (keeps JSON small)
**Storage Format**: JSON (simple, human-readable, easy to debug)
- Each audio file β 1 JSON file
- Typical size: ~20KB per file (without spectrogram)
- Total: ~200KB for 10 files
---
### Step 2: Runtime Patching
**Input**:
- Precomputed JSON
- User parameters (threshold, metric, constraint type)
**Process**:
1. Load metric array (entropy or perplexity)
2. Apply patching strategy
3. Return patch boundaries
**Patching Strategies**:
#### A. Global Threshold
```python
def patch_global_threshold(metric, threshold):
patches = []
current_patch = []
for i, value in enumerate(metric):
current_patch.append(i)
if value > threshold:
patches.append(current_patch)
current_patch = []
if current_patch:
patches.append(current_patch)
return patches
```
#### B. Additive Monotonicity
```python
def patch_additive_monotonic(metric, threshold):
patches = []
current_patch = [0]
for i in range(1, len(metric)):
delta = metric[i] - metric[i-1]
if delta > threshold:
patches.append(current_patch)
current_patch = [i]
else:
current_patch.append(i)
if current_patch:
patches.append(current_patch)
return patches
```
#### C. Multiplicative Monotonicity
```python
def patch_multiplicative_monotonic(metric, threshold):
patches = []
current_patch = [0]
for i in range(1, len(metric)):
if metric[i-1] > 0: # Avoid division by zero
ratio = metric[i] / metric[i-1]
else:
ratio = 1.0
if ratio > threshold:
patches.append(current_patch)
current_patch = [i]
else:
current_patch.append(i)
if current_patch:
patches.append(current_patch)
return patches
```
---
## Gradio UI
### Layout
```
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β BLT Patching Visualization Explorer β
βββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β Controls β
ββββββββββββββββββββ¬βββββββββββββββββββββββββββββββ€
β Audio File: β Patching Parameters: β
β [Dropdown βΌ] β Metric: β
β β β Entropy β Perplexity β
β 1089-134691-0016 β β
β Duration: 7.2s β Constraint: β
β Tokens: 289 β β Global Threshold β
β β β Additive Monotonic β
β Transcript: β β Multiplicative Monotonicβ
β "..." (truncated)β β
β β Threshold: [2.0 βββββββ] β
β β (range: 0.0 - 10.0) β
β β β
β β [Apply Patching] β
ββββββββββββββββββββ΄βββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β Waveform + Patch Boundaries β
β [Plotly Interactive Plot] β
β - X-axis: Time (sec) β
β - Y-axis: Amplitude β
β - Red vertical lines: Patch boundaries β
βββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β Spectrogram + Patch Boundaries β
β [Plotly Interactive Plot] β
β - X-axis: Time (sec) β
β - Y-axis: Frequency (Hz) β
β - Color: Magnitude (dB) β
β - Red vertical lines: Patch boundaries β
βββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β Entropy/Perplexity + Patch Boundaries β
β [Plotly Interactive Plot] β
β - X-axis: Token position β
β - Y-axis: Metric value β
β - Blue line: Metric values β
β - Red horizontal line: Threshold β
β - Gray vertical lines: Patch boundaries β
βββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β Patch Statistics β
β Total Patches: 42 β
β Avg Size: 6.9 tokens β
β Min Size: 2 tokens β
β Max Size: 18 tokens β
β β
β [Bar Chart: Patch Size Distribution] β
βββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββ
β Audio Playback β
β [βΆ Play Full Audio] β
β [βΆ Play Until Next Boundary] (from current pos)β
β β
β Current Position: 2.34s (Token 94, Patch 15) β
β Next Boundary: 2.89s (Token 116) β
βββββββββββββββββββββββββββββββββββββββββββββββββββ
```
### Interactions
1. **Select Audio**: Dropdown changes which precomputed data is loaded
2. **Adjust Parameters**: Sliders/radio buttons update patching in real-time
3. **Click Plots**: Click on waveform/spectrogram to set playback position
4. **Play Until Boundary**: Plays from current position until next patch boundary
- Useful for hearing what's in a single patch
- Automatically stops at boundary
---
## Implementation
### File Structure
```
apps/patch_view/
βββ precompute.py # Offline: Compute entropy/perplexity for all samples
βββ app.py # Gradio app
βββ patching.py # Patching strategies
βββ visualization.py # Plotly plot generation
βββ audio.py # Audio playback utilities
βββ README.md # Usage instructions
```
### Dependencies
```python
# requirements.txt
gradio>=4.0
plotly>=5.0
numpy>=1.24
torch>=2.0
torchaudio>=2.0
librosa>=0.10
soundfile>=0.12
```
### Core Functions
#### precompute.py
```python
import torch
import torchaudio
import librosa
import numpy as np
import json
from pathlib import Path
def load_entropy_model(checkpoint_path):
"""Load entropy model from checkpoint"""
# Load from archive/checkpoints/audio_peoplespeech_50k_scratch/best
pass
def compute_entropies(audio_path, entropy_model):
"""
Load audio, encode with WavTokenizer, compute entropies
Returns:
tokens: np.array of token IDs
entropies: np.array of entropy values (bits)
"""
pass
def compute_spectrogram(audio, sr=24000):
"""
Generate mel-spectrogram for visualization
Returns:
times: np.array of time points
frequencies: np.array of frequency bins
magnitudes: 2D np.array (freq x time)
"""
S = librosa.feature.melspectrogram(
y=audio, sr=sr, n_mels=128, fmax=8000
)
S_db = librosa.power_to_db(S, ref=np.max)
times = librosa.frames_to_time(
np.arange(S.shape[1]), sr=sr, hop_length=512
)
frequencies = librosa.mel_frequencies(n_mels=128, fmax=8000)
return times, frequencies, S_db
def precompute_all():
"""Precompute entropy/perplexity for all test-10 samples"""
entropy_model = load_entropy_model(
"archive/checkpoints/audio_peoplespeech_50k_scratch/best"
)
test_dir = Path("data/test-10")
output_dir = Path("data/test-10/precomputed")
output_dir.mkdir(exist_ok=True)
for audio_file in sorted(test_dir.glob("*.flac")):
print(f"Processing {audio_file.name}...")
# Load audio
audio, sr = librosa.load(audio_file, sr=24000, mono=True)
# Compute tokens and entropies
tokens, entropies = compute_entropies(audio_file, entropy_model)
# Compute perplexities
perplexities = 2 ** entropies
# Compute spectrogram
times, freqs, mags = compute_spectrogram(audio, sr)
# Load transcript
txt_file = audio_file.with_suffix(".txt")
transcript = txt_file.read_text().strip() if txt_file.exists() else ""
# Save
data = {
"file_id": audio_file.stem,
"audio_path": str(audio_file),
"transcript": transcript,
"audio_duration_sec": float(len(audio) / sr),
"sample_rate": int(sr),
"tokens": tokens.tolist(),
"entropies": entropies.tolist(),
"perplexities": perplexities.tolist(),
"spectrogram": {
"times": times.tolist(),
"frequencies": freqs.tolist(),
"magnitudes": mags.tolist()
}
}
output_file = output_dir / f"{audio_file.stem}.json"
with open(output_file, 'w') as f:
json.dump(data, f, indent=2)
print(f" Saved to {output_file}")
if __name__ == "__main__":
precompute_all()
```
#### patching.py
```python
import numpy as np
from typing import List
def patch_global_threshold(metric: np.ndarray, threshold: float) -> List[List[int]]:
"""Patch when metric exceeds threshold"""
patches = []
current_patch = []
for i, value in enumerate(metric):
current_patch.append(i)
if value > threshold:
patches.append(current_patch)
current_patch = []
if current_patch:
patches.append(current_patch)
return patches
def patch_additive_monotonic(metric: np.ndarray, threshold: float) -> List[List[int]]:
"""Patch when metric increase exceeds threshold"""
patches = []
current_patch = [0]
for i in range(1, len(metric)):
delta = metric[i] - metric[i-1]
if delta > threshold:
patches.append(current_patch)
current_patch = [i]
else:
current_patch.append(i)
if current_patch:
patches.append(current_patch)
return patches
def patch_multiplicative_monotonic(metric: np.ndarray, threshold: float) -> List[List[int]]:
"""Patch when metric ratio exceeds threshold"""
patches = []
current_patch = [0]
for i in range(1, len(metric)):
if metric[i-1] > 1e-6: # Avoid division by zero
ratio = metric[i] / metric[i-1]
else:
ratio = 1.0
if ratio > threshold:
patches.append(current_patch)
current_patch = [i]
else:
current_patch.append(i)
if current_patch:
patches.append(current_patch)
return patches
def apply_patching(metric: np.ndarray,
constraint: str,
threshold: float) -> List[List[int]]:
"""
Apply patching strategy
Args:
metric: Entropy or perplexity values
constraint: "global", "additive", or "multiplicative"
threshold: Threshold value
Returns:
List of patches (each patch is list of token indices)
"""
if constraint == "global":
return patch_global_threshold(metric, threshold)
elif constraint == "additive":
return patch_additive_monotonic(metric, threshold)
elif constraint == "multiplicative":
return patch_multiplicative_monotonic(metric, threshold)
else:
raise ValueError(f"Unknown constraint: {constraint}")
def compute_patch_statistics(patches: List[List[int]]) -> dict:
"""Compute statistics about patches"""
sizes = [len(p) for p in patches]
return {
"num_patches": len(patches),
"avg_size": np.mean(sizes),
"min_size": np.min(sizes),
"max_size": np.max(sizes),
"median_size": np.median(sizes),
"std_size": np.std(sizes),
"sizes": sizes
}
```
#### visualization.py
```python
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import numpy as np
def create_visualization(data: dict, patches: List[List[int]],
metric_name: str, threshold: float):
"""
Create 4-panel visualization
Args:
data: Precomputed data dict
patches: Patch boundaries
metric_name: "entropy" or "perplexity"
threshold: Threshold value
Returns:
Plotly figure
"""
fig = make_subplots(
rows=4, cols=1,
subplot_titles=(
'Waveform',
'Spectrogram',
f'{metric_name.capitalize()} + Patch Boundaries',
'Patch Size Distribution'
),
specs=[
[{"type": "scatter"}],
[{"type": "heatmap"}],
[{"type": "scatter"}],
[{"type": "bar"}]
],
vertical_spacing=0.08,
row_heights=[0.2, 0.3, 0.3, 0.2]
)
# Get metric data
metric = np.array(data['entropies'] if metric_name == 'entropy'
else data['perplexities'])
# Calculate patch boundary times
tokens_per_sec = 40 # WavTokenizer rate
boundary_times = []
for patch in patches:
if patch:
boundary_times.append(patch[0] / tokens_per_sec)
# 1. Waveform (simplified - just show patch boundaries)
duration = data['audio_duration_sec']
fig.add_trace(
go.Scatter(
x=[0, duration],
y=[0, 0],
mode='lines',
name='Audio',
line=dict(color='lightgray', width=1)
),
row=1, col=1
)
# Add patch boundaries to waveform
for t in boundary_times:
fig.add_vline(
x=t, line_width=1, line_dash="solid",
line_color="red", opacity=0.5,
row=1, col=1
)
# 2. Spectrogram
spec = data['spectrogram']
fig.add_trace(
go.Heatmap(
x=spec['times'],
y=spec['frequencies'],
z=spec['magnitudes'],
colorscale='Viridis',
showscale=False
),
row=2, col=1
)
# Add patch boundaries to spectrogram
for t in boundary_times:
fig.add_vline(
x=t, line_width=1, line_dash="solid",
line_color="red", opacity=0.7,
row=2, col=1
)
# 3. Entropy/Perplexity plot
token_positions = np.arange(len(metric))
fig.add_trace(
go.Scatter(
x=token_positions,
y=metric,
mode='lines',
name=metric_name.capitalize(),
line=dict(color='blue', width=2)
),
row=3, col=1
)
# Add threshold line
fig.add_hline(
y=threshold, line_width=2, line_dash="dash",
line_color="red", opacity=0.7,
annotation_text=f"Threshold: {threshold:.2f}",
row=3, col=1
)
# Add patch boundaries
for patch in patches:
if patch:
fig.add_vline(
x=patch[0], line_width=1, line_dash="solid",
line_color="gray", opacity=0.5,
row=3, col=1
)
# 4. Patch size distribution
sizes = [len(p) for p in patches]
size_counts = {}
for size in sizes:
size_counts[size] = size_counts.get(size, 0) + 1
fig.add_trace(
go.Bar(
x=list(size_counts.keys()),
y=list(size_counts.values()),
name='Patch Sizes',
marker_color='steelblue'
),
row=4, col=1
)
# Update layout
fig.update_xaxes(title_text="Time (s)", row=1, col=1)
fig.update_xaxes(title_text="Time (s)", row=2, col=1)
fig.update_yaxes(title_text="Frequency (Hz)", row=2, col=1)
fig.update_xaxes(title_text="Token Position", row=3, col=1)
fig.update_yaxes(title_text=metric_name.capitalize(), row=3, col=1)
fig.update_xaxes(title_text="Patch Size (tokens)", row=4, col=1)
fig.update_yaxes(title_text="Count", row=4, col=1)
fig.update_layout(
height=1200,
showlegend=False,
hovermode='x unified'
)
return fig
```
#### audio.py
```python
import soundfile as sf
import numpy as np
from pathlib import Path
class AudioPlayer:
"""Handle audio playback for patches"""
def __init__(self, audio_path: str, sample_rate: int = 24000):
self.audio, self.sr = sf.read(audio_path)
self.sample_rate = sample_rate
self.current_position = 0 # In samples
def get_full_audio(self):
"""Return full audio for playback"""
return self.sr, self.audio
def play_until_boundary(self, patches: List[List[int]],
current_token: int) -> tuple:
"""
Get audio from current position until next patch boundary
Args:
patches: List of patches
current_token: Current token position
Returns:
(sample_rate, audio_segment)
"""
# Find which patch contains current token
current_patch_idx = None
for i, patch in enumerate(patches):
if current_token in patch:
current_patch_idx = i
break
if current_patch_idx is None:
return self.sr, np.array([])
# Get tokens in current patch from current position onward
current_patch = patches[current_patch_idx]
start_token = current_token
end_token = current_patch[-1]
# Convert to audio samples (40 tokens/sec)
tokens_per_sec = 40
start_sample = int(start_token / tokens_per_sec * self.sr)
end_sample = int((end_token + 1) / tokens_per_sec * self.sr)
# Extract segment
segment = self.audio[start_sample:end_sample]
return self.sr, segment
```
#### app.py
```python
import gradio as gr
import json
import numpy as np
from pathlib import Path
from patching import apply_patching, compute_patch_statistics
from visualization import create_visualization
from audio import AudioPlayer
# Load all precomputed data
PRECOMPUTED_DIR = Path("data/test-10/precomputed")
precomputed_data = {}
def load_precomputed_data():
"""Load all precomputed JSON files"""
for json_file in PRECOMPUTED_DIR.glob("*.json"):
with open(json_file) as f:
data = json.load(f)
precomputed_data[data['file_id']] = data
def get_audio_choices():
"""Get list of available audio files"""
return sorted(precomputed_data.keys())
def process_patching(file_id, metric_name, constraint, threshold):
"""
Apply patching and generate visualization
Returns:
figure, stats_text, audio
"""
# Get data
data = precomputed_data[file_id]
# Select metric
metric = np.array(data['entropies'] if metric_name == 'Entropy'
else data['perplexities'])
# Apply patching
patches = apply_patching(metric, constraint.lower(), threshold)
# Compute statistics
stats = compute_patch_statistics(patches)
# Generate visualization
fig = create_visualization(data, patches, metric_name.lower(), threshold)
# Format statistics
stats_text = f"""
**Patch Statistics:**
- Total Patches: {stats['num_patches']}
- Average Size: {stats['avg_size']:.2f} tokens
- Min Size: {stats['min_size']} tokens
- Max Size: {stats['max_size']} tokens
- Median Size: {stats['median_size']:.1f} tokens
- Std Dev: {stats['std_size']:.2f} tokens
"""
# Load audio
audio_path = data['audio_path']
player = AudioPlayer(audio_path)
sr, audio = player.get_full_audio()
return fig, stats_text, (sr, audio), patches
def play_until_boundary(file_id, current_token, patches):
"""Play audio from current token until next boundary"""
data = precomputed_data[file_id]
audio_path = data['audio_path']
player = AudioPlayer(audio_path)
sr, segment = player.play_until_boundary(patches, current_token)
return (sr, segment)
# Gradio Interface
def create_app():
load_precomputed_data()
with gr.Blocks(title="BLT Patching Visualization") as app:
gr.Markdown("# BLT Patching Visualization Explorer")
gr.Markdown("Explore entropy-based patching strategies on audio")
with gr.Row():
# Left column: Controls
with gr.Column(scale=1):
gr.Markdown("### Audio Selection")
audio_dropdown = gr.Dropdown(
choices=get_audio_choices(),
value=get_audio_choices()[0],
label="Audio File"
)
file_info = gr.Markdown()
gr.Markdown("### Patching Parameters")
metric_radio = gr.Radio(
choices=["Entropy", "Perplexity"],
value="Entropy",
label="Metric"
)
constraint_radio = gr.Radio(
choices=["Global", "Additive", "Multiplicative"],
value="Global",
label="Constraint Type"
)
threshold_slider = gr.Slider(
minimum=0.0,
maximum=10.0,
value=2.0,
step=0.1,
label="Threshold"
)
apply_btn = gr.Button("Apply Patching", variant="primary")
# Visualization area
with gr.Column(scale=2):
plot_output = gr.Plot(label="Visualization")
stats_output = gr.Markdown()
# Audio playback
gr.Markdown("### Audio Playback")
with gr.Row():
audio_output = gr.Audio(label="Full Audio", type="numpy")
with gr.Row():
current_token_input = gr.Number(
value=0,
label="Current Token Position",
precision=0
)
play_boundary_btn = gr.Button("βΆ Play Until Next Boundary")
boundary_audio = gr.Audio(label="Patch Audio", type="numpy")
# State to store patches
patches_state = gr.State([])
# Update file info when audio changes
def update_file_info(file_id):
data = precomputed_data[file_id]
info = f"""
**Duration:** {data['audio_duration_sec']:.2f}s
**Tokens:** {len(data['tokens'])}
**Transcript:** {data['transcript'][:100]}...
"""
return info
audio_dropdown.change(
update_file_info,
inputs=[audio_dropdown],
outputs=[file_info]
)
# Apply patching
apply_btn.click(
process_patching,
inputs=[audio_dropdown, metric_radio, constraint_radio, threshold_slider],
outputs=[plot_output, stats_output, audio_output, patches_state]
)
# Play until boundary
play_boundary_btn.click(
play_until_boundary,
inputs=[audio_dropdown, current_token_input, patches_state],
outputs=[boundary_audio]
)
# Initialize
app.load(
update_file_info,
inputs=[audio_dropdown],
outputs=[file_info]
)
return app
if __name__ == "__main__":
app = create_app()
app.launch(server_name="0.0.0.0", server_port=7860)
```
---
## Development Steps
### Step 1: Precomputation (1 day)
1. β
Adapt existing entropy analysis script
2. β
Load entropy model checkpoint
3. β
Process all 10 audio files
4. β
Save JSON files
**Command**:
```bash
uv run python apps/patch_view/precompute.py
```
### Step 2: Core Patching (0.5 days)
1. β
Implement 3 patching strategies
2. β
Test on sample data
3. β
Validate outputs
### Step 3: Visualization (1 day)
1. β
Create 4-panel Plotly figure
2. β
Add patch boundaries
3. β
Test interactivity
### Step 4: Gradio UI (1 day)
1. β
Build basic interface
2. β
Wire up controls
3. β
Add audio playback
### Step 5: Audio Playback (0.5 days)
1. β
Implement "play until boundary"
2. β
Test timing accuracy
### Step 6: Polish (0.5 days)
1. β
Fix bugs
2. β
Improve layout
3. β
Add documentation
**Total Time**: ~4 days
---
## Success Criteria
### Functional
- β
All 10 audio files precomputed
- β
3 patching strategies working
- β
Real-time threshold adjustment
- β
Interactive visualizations
- β
"Play until boundary" feature
### Performance
- β
<1s latency for parameter changes
- β
Smooth plot interactions
- β
Accurate audio playback timing
### Quality
- β
Clear visualizations
- β
Intuitive controls
- β
No crashes on edge cases (threshold=0, etc.)
---
## Future Enhancements (Optional)
1. **Click-to-play**: Click on waveform β play from that position
2. **Patch highlighting**: Click patch β highlight in all plots
3. **Comparison view**: Show 2 strategies side-by-side
4. **Statistics table**: Per-patch details in table
5. **Download data**: Export patches as JSON
These are nice-to-have but not essential for v1.
|