fix README demo img

README.md

@@ -43,25 +43,21 @@ Built for the Hugging Face Hackathon. Runs entirely on local models inside a Gra
 
 ## How It Works
 
-
-| Step       | What Happens                                                                                                                                          | Model                             |
-| ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------- |
-| **Clone**  | Parent records or uploads 15–30s of audio. Speaker embedding is extracted and cached.                                                                 | Qwen3-TTS-1.7B Base               |
-| **Listen** | Story plays in the cloned voice as interruptible sentence chunks. Falls back to CustomVoice 0.6B stock voice (speaker "vivian") if no clone.          | Qwen3-TTS-1.7B / CustomVoice 0.6B |
-| **Ask**    | Child taps Ask → narration pauses, microphone auto-starts. When recording stops, the question is sent directly to the Q&A audio model.                | LFM2.5-Audio-1.5B                 |
-| **Answer** | A short grounded answer is generated from the story context and spoken by the low-latency Q&A audio model. It does not use the cloned narrator voice. | LFM2.5-Audio-1.5B                 |
-| **Resume** | Story continues from where it left off. Play also pauses on tab switch.                                                                               | Cached chunks                     |
-
+| Step | What Happens | Model |
+|---|---|---|
+| **Clone** | Parent records or uploads 15–30s of audio. Speaker embedding is extracted and cached. | Qwen3-TTS-1.7B Base |
+| **Listen** | Story plays in the cloned voice as interruptible sentence chunks. Falls back to CustomVoice 0.6B stock voice (speaker "vivian") if no clone. | Qwen3-TTS-1.7B / CustomVoice 0.6B |
+| **Ask** | Child taps Ask → narration pauses, microphone auto-starts. When recording stops, the question is sent directly to the Q&A audio model. | LFM2.5-Audio-1.5B |
+| **Answer** | A short grounded answer is generated from the story context and spoken by the low-latency Q&A audio model. It does not use the cloned narrator voice. | LFM2.5-Audio-1.5B |
+| **Resume** | Story continues from where it left off. Play also pauses on tab switch. | Cached chunks |
 
 ## Models
 
-
-| Model                                                                                     | Role                                                          | Size        |
-| ----------------------------------------------------------------------------------------- | ------------------------------------------------------------- | ----------- |
-| [Qwen3-TTS-1.7B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base)               | Zero-shot voice cloning + TTS                                 | 1.7B params |
-| [Qwen3-TTS-0.6B-CustomVoice](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice) | Fast stock-voice TTS (predefined speakers)                    | 0.6B params |
-| [LiquidAI/LFM2.5-Audio-1.5B](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B)           | End-to-end story Q&A with audio input and spoken audio output | 1.5B params |
-
+| Model | Role | Size |
+|---|---|---|
+| [Qwen3-TTS-1.7B-Base](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base) | Zero-shot voice cloning + TTS | 1.7B params |
+| [Qwen3-TTS-0.6B-CustomVoice](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice) | Fast stock-voice TTS (predefined speakers) | 0.6B params |
+| [LiquidAI/LFM2.5-Audio-1.5B](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B) | End-to-end story Q&A with audio input and spoken audio output | 1.5B params |
 
 The stock narration model and LFM Q&A model are preloaded at startup for fast response times. The 1.7B cloning model is loaded when cloning or cloned narration is needed.
 
@@ -76,32 +72,27 @@ The stock narration model and LFM Q&A model are preloaded at startup for fast re
 
 ## System Requirements
 
-
-| GPU                 | VRAM  | Status        | Notes                                                                                                                            |
-| ------------------- | ----- | ------------- | -------------------------------------------------------------------------------------------------------------------------------- |
-| Nvidia A10G (24 GB) | 24 GB | ✅ Recommended | All three models load comfortably; narration + Q&A run without memory pressure                                                   |
-| Nvidia T4 (16 GB)   | 16 GB | ⚠️ Functional | Works but is tight — voice cloning model may OOM if loaded concurrently with LFM; restart may be needed between heavy operations |
-| CPU only            | —     | ❌ Not viable  | LFM2.5-Audio and Qwen3-TTS inference is too slow for real-time use                                                               |
-
+| GPU | VRAM | Status | Notes |
+|---|---|---|---|
+| Nvidia A10G (24 GB) | 24 GB | ✅ Recommended | All three models load comfortably; narration + Q&A run without memory pressure |
+| Nvidia T4 (16 GB) | 16 GB | ⚠️ Functional | Works but is tight — voice cloning model may OOM if loaded concurrently with LFM; restart may be needed between heavy operations |
+| CPU only | — | ❌ Not viable | LFM2.5-Audio and Qwen3-TTS inference is too slow for real-time use |
 
 **Hugging Face Spaces:**
-
 - **A10G Small** — confirmed working, recommended for the hackathon demo
 - **T4 Small** — runs with limitations; recommend disabling concurrent model loading
 
-HuggingFace Space Hardware Options
+![HuggingFace Space Hardware Options](docs/hf_spec.png)
 
 **Memory breakdown (approximate):**
 
-
-| Model                               | VRAM (bfloat16) |
-| ----------------------------------- | --------------- |
-| LFM2.5-Audio-1.5B                   | ~3 GB           |
-| Qwen3-TTS-0.6B-CustomVoice          | ~1.2 GB         |
-| Qwen3-TTS-1.7B-Base (cloning)       | ~3.4 GB         |
-| KV cache + activations at inference | ~1–2 GB         |
-| **Total (all models loaded)**       | **~8–9 GB**     |
-
+| Model | VRAM (bfloat16) |
+|---|---|
+| LFM2.5-Audio-1.5B | ~3 GB |
+| Qwen3-TTS-0.6B-CustomVoice | ~1.2 GB |
+| Qwen3-TTS-1.7B-Base (cloning) | ~3.4 GB |
+| KV cache + activations at inference | ~1–2 GB |
+| **Total (all models loaded)** | **~8–9 GB** |
 
 The 1.7B cloning model is loaded on demand (not at startup), so idle VRAM usage is ~5–6 GB with only the narration and Q&A models preloaded.
 
@@ -152,20 +143,18 @@ python app.py
 
 ## Stories Included
 
-
-| Story                              | Words | Source              |
-| ---------------------------------- | ----- | ------------------- |
-| The Tale of Peter Rabbit           | 948   | Beatrix Potter      |
-| The Tale of Benjamin Bunny         | 1,118 | Beatrix Potter      |
-| The Tale of Jemima Puddle-Duck     | 1,245 | Beatrix Potter      |
-| The Tale of Tom Kitten             | 691   | Beatrix Potter      |
-| The History of Tom Thumb           | 2,912 | Traditional         |
-| The Story of the Three Little Pigs | 956   | Traditional         |
-| The Little Red Hen                 | 1,295 | Traditional         |
-| The Little Gingerbread Man         | 1,823 | Traditional         |
-| The Sleeping Beauty                | 1,783 | Traditional         |
-| The Adventures of Puss in Boots    | 503   | Traditional (verse) |
-
+| Story | Words | Source |
+|---|---|---|
+| The Tale of Peter Rabbit | 948 | Beatrix Potter |
+| The Tale of Benjamin Bunny | 1,118 | Beatrix Potter |
+| The Tale of Jemima Puddle-Duck | 1,245 | Beatrix Potter |
+| The Tale of Tom Kitten | 691 | Beatrix Potter |
+| The History of Tom Thumb | 2,912 | Traditional |
+| The Story of the Three Little Pigs | 956 | Traditional |
+| The Little Red Hen | 1,295 | Traditional |
+| The Little Gingerbread Man | 1,823 | Traditional |
+| The Sleeping Beauty | 1,783 | Traditional |
+| The Adventures of Puss in Boots | 503 | Traditional (verse) |
 
 All stories are public domain from [Project Gutenberg](https://www.gutenberg.org/).
 
@@ -188,6 +177,7 @@ All inference runs on the Hugging Face Space GPU. Voice samples, story text, and
 Hackathon project. Stories are public domain.
 test push verification
 
+
 ## Application Demo
 
 # MomsVoice — Demo Walkthrough
@@ -198,7 +188,7 @@ Step-by-step guide through the app with screenshots.
 
 ## Step 1: Explore the Story Shelf
 
-Explore Space
+![Explore Space](docs/demo01.png)
 
 Open the **Explore Space** tab to browse available stories displayed as warm bookshelf cards. Each card shows the cover art, title, author, and a short excerpt. Click **"Tap to Play"** on any card to open it in My Library, or click **"More Info"** for the full story description.
 
@@ -208,7 +198,7 @@ The featured story highlights the current pick. All 10 stories are public domain
 
 ## Step 2: Open My Library and Start Narration
 
-My Library — Now Playing
+![My Library — Now Playing](docs/demo02.png)
 
 Switch to the **My Library** tab. Click any story card to load it into the **Now Playing** panel on the right. The panel shows:
 
@@ -223,7 +213,7 @@ Narration starts immediately, playing one paragraph at a time using the TTS mode
 
 ## Step 3: Ask a Question About the Story
 
-Voice Q&A Panel
+![Voice Q&A Panel](docs/demo03.png)
 
 Scroll down in the Library panel to find the **Ask About the Story** section. Click **❓ Ask a Question** — narration pauses automatically and the microphone starts recording.
 
@@ -233,12 +223,11 @@ Speak your question naturally (e.g. *"What did Puss in Boots do to help his mast
 
 ## Step 4: Hear the Spoken Answer (LFM2.5-Audio)
 
-LFM Answer Audio
+![LFM Answer Audio](docs/demo04.png)
 
 The recorded question waveform appears in the audio widget. Below it, the **LFM2.5-Audio** model generates a grounded answer in 1–2 sentences, based only on the current story context.
 
 The answer is delivered in two ways simultaneously:
-
 - **Answer text** shown inline (e.g. *"Puss in Boots, a poor man, bargained for boots and a bag, and Grimalkin, ailient rabbit, rescued him from a king's wrath."*)
 - **Answer Audio** waveform auto-plays the spoken response
 
@@ -248,10 +237,9 @@ After the answer finishes, narration resumes from where it paused.
 
 ## Step 5: Open Clone Voice Studio and Record Your Voice
 
-Clone Studio — Recording
+![Clone Studio — Recording](docs/demo05_clone.png)
 
 Go to the **Clone Voice Studio** tab. Fill in:
-
 - **Voice Nickname** — a name for this profile (e.g. *"Mom"*, *"Grandpa Joe"*)
 - **Voice Gender Avatar** — Female or Male
 
@@ -261,7 +249,7 @@ A story script is displayed to read aloud. Click the **Record** button and read
 
 ## Step 6: Analyze & Synthesize the Vocal Profile
 
-Clone Studio — Processing
+![Clone Studio — Processing](docs/demo06_clone.png)
 
 Click **Analyze & Synthesize Customized Vocal Profile**. The **Status Pipeline Visualizer** on the right tracks progress through extraction, de-noising, and pitch tuning stages.
 
@@ -271,10 +259,9 @@ A progress bar shows synthesis percentage (e.g. *"Generating voice preview... 70
 
 ## Step 7: Voice Profile Ready
 
-Clone Studio — Complete
+![Clone Studio — Complete](docs/demo07_clone.png)
 
 When synthesis completes, the Status Pipeline Visualizer shows:
-
 - Your **avatar** and nickname with a **"Cloned successfully"** badge
 - *"Synthesized today using Qwen3-TTS voice cloning"*
 - A **preview audio player** — tap Play to hear a short sample in your cloned voice
@@ -286,8 +273,8 @@ The profile is saved to disk and will persist across Space restarts.
 
 ## Step 8: Story Narration in Your Cloned Voice
 
-Narration with Cloned Voice
+![Narration with Cloned Voice](docs/demo08_clone.png)
 
 Return to **My Library** and select a story. The Now Playing panel shows **Active Narrator: [your nickname]** — confirming the cloned voice is active.
 
-Narration plays in your recorded voice, paragraph by paragraph (*"Paragraph 1 / 32"*). The story text scrolls in the reader below the player. All TTS inference runs locally on the Space GPU — no audio leaves the server.
+Narration plays in your recorded voice, paragraph by paragraph (*"Paragraph 1 / 32"*). The story text scrolls in the reader below the player. All TTS inference runs locally on the Space GPU — no audio leaves the server.