Update README.md

README.md

@@ -1,42 +1,43 @@
 ---
 title: Haseeb's TTS
-emoji: 🎧
+emoji: 🚀
 colorFrom: indigo
 colorTo: purple
 sdk: streamlit
-sdk_version: 1.32.0
+sdk_version: 1.54.0
 python_version: '3.10'
 app_file: app.py
 pinned: false
 license: apache-2.0
 thumbnail: >-
-  https://cdn-uploads.huggingface.co/production/uploads/652ac2e92aa5b27c77cba196/YwfGGlu6hJYzYGiwjPHbX.png
+  https://cdn-uploads.huggingface.co/production/uploads/652ac2e92aa5b27c77cba196/6Y7vGO0SQfVaCj9CYXzzf.png
 ---
 
 # 🎧 Haseeb's TTS (Audiobook MP3 Generator)
 
 Generate audiobook-style narration using **Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice** with a Streamlit UI built for long chapters.
 
-## Why Transformers from source?
-This model uses a newer architecture (`qwen3_tts`). If your Space installs an older Transformers release, it may fail with:
+## Why `qwen-tts` instead of `transformers.pipeline()`?
+The model uses the `qwen3_tts` architecture. Some Transformers builds in hosted environments may not recognize it.
+This Space uses Qwen’s official **`qwen-tts`** package which supports:
+- `generate_custom_voice(text, language, speaker, instruct, ...)`
+- `get_supported_speakers()` / `get_supported_languages()`  
 
-> "Transformers does not recognize this architecture"
-
-To fix that, this Space installs **Transformers from GitHub** (latest) and uses `trust_remote_code=True`.
+(As shown in Qwen’s official Qwen3-TTS repo docs.) :contentReference[oaicite:1]{index=1}
 
 ## Features
 - ✅ **MP3 output** (no ffmpeg needed)
 - ✅ **Batch mode**: upload multiple `.txt` files → get multiple MP3s + **ZIP download**
 - ✅ **Long chapters (10,000+ chars)** via chunking + stitching
-- ✅ **Language Support** (dropdown steering)
-- ✅ **Voices / Speakers** (auto-detected if exposed + custom speaker field)
-- ✅ **Instruction Control** (style/emotion/pacing prompt)
+- ✅ **Language Support** (dropdown; auto-populated from the model when possible)
+- ✅ **Voices / Speakers** (auto-populated from the model when possible)
+- ✅ **Instruction Control** (style/emotion/pacing)
 
 ## How to use
 
 ### Single chapter
 1. Paste text (or upload a single `.txt`)
-2. Pick language, voice/speaker (optional), instruction
+2. Choose language, speaker, instruction
 3. Click **Generate MP3**
 
 ### Batch mode
@@ -47,7 +48,7 @@ To fix that, this Space installs **Transformers from GitHub** (latest) and uses
 
 ## Tips for audiobooks
 - Chunk size: **1200–1800 chars** is usually stable for long narration.
-- Add silence between chunks: **200–350 ms** reduces audible joins.
+- Silence between chunks: **200–350 ms** reduces audible joins.
 - If memory is tight, reduce:
   - chunk size
   - `max_new_tokens`