docs: update text-processing-rs description with multilingual support (#365)

## Summary

- Update text-processing-rs description in README and PostProcessing
docs to reflect current capabilities
- Now mentions ITN + TN support across 7 languages (EN, DE, ES, FR, HI,
JA, ZH)
- Added 100% NeMo test compatibility note (3,011 tests passing)

## Test plan

- [x] Docs-only change, no code affected
<!-- devin-review-badge-begin -->

---

<a href="https://app.devin.ai/review/fluidinference/fluidaudio/pull/365"
target="_blank">
  <picture>
<source media="(prefers-color-scheme: dark)"
srcset="https://static.devin.ai/assets/gh-open-in-devin-review-dark.svg?v=1">
<img
src="https://static.devin.ai/assets/gh-open-in-devin-review-light.svg?v=1"
alt="Open with Devin">
  </picture>
</a>
<!-- devin-review-badge-end -->

Documentation/ASR/PostProcessing.md

@@ -1,8 +1,12 @@
-# Post-Processing ASR Output
+# Text Processing
+
+## Overview
+
+**[text-processing-rs](https://github.com/FluidInference/text-processing-rs)** provides both Inverse Text Normalization (ITN) and Text Normalization (TN) across 7 languages (EN, DE, ES, FR, HI, JA, ZH). 100% NeMo test compatibility (3,011 tests). Rust port of [NVIDIA NeMo Text Processing](https://github.com/NVIDIA/NeMo-text-processing) with Swift wrapper.
 
 ## Inverse Text Normalization (ITN)
 
-Inverse Text Normalization converts spoken-form ASR output to written form:
+ITN converts spoken-form ASR output to written form — useful for post-processing ASR transcriptions:
 
 | Input (spoken) | Output (written) |
 |----------------|------------------|
@@ -12,17 +16,23 @@ Inverse Text Normalization converts spoken-form ASR output to written form:
 | "two thirty pm" | "2:30 p.m." |
 | "test at gmail dot com" | "test@gmail.com" |
 
-## Post-Processing Tools
+## Text Normalization (TN)
 
-| Tool | Description | Language |
-|------|-------------|----------|
-| **[text-processing-rs](https://github.com/FluidInference/text-processing-rs)** | Inverse Text Normalization (ITN) - converts spoken-form ASR output to written form. Rust port of [NVIDIA NeMo Text Processing](https://github.com/NVIDIA/NeMo-text-processing) with Swift wrapper. | Rust, Swift |
+TN converts written-form text to spoken form — useful for TTS preprocessing:
 
-## Using ITN with FluidAudio
+| Input (written) | Output (spoken) |
+|-----------------|-----------------|
+| "123" | "one hundred twenty three" |
+| "$5.50" | "five dollars and fifty cents" |
+| "January 5, 2025" | "january fifth twenty twenty five" |
+| "2:30 PM" | "two thirty p m" |
+| "1st" | "first" |
 
-FluidAudio includes optional support for text-processing-rs through the `TextNormalizer` class. The library uses dynamic loading, so it's completely optional - if not linked, `normalize()` returns the input unchanged.
+## Using with FluidAudio
 
-### Basic Usage
+FluidAudio includes optional support for text-processing-rs through the `TextNormalizer` class. The library uses dynamic loading, so it's completely optional — if not linked, `normalize()` returns the input unchanged.
+
+### ITN (Spoken to Written)
 
 ```swift
 import FluidAudio
@@ -39,20 +49,31 @@ let result = normalizer.normalize("two hundred dollars")
 // Returns "$200" (with native library) or "two hundred dollars" (without)
 ```
 
+### TN (Written to Spoken)
+
+```swift
+// Convert written text to spoken form for TTS
+let spoken = normalizer.tnNormalize("$5.50")
+// Returns "five dollars and fifty cents"
+
+let spoken = normalizer.tnNormalize("January 5, 2025")
+// Returns "january fifth twenty twenty five"
+```
+
 ### With ASR Results
 
 ```swift
 // Transcribe audio
 let asrResult = try await asrManager.transcribe(samples, source: .system)
 
-// Normalize the result
+// Normalize the result (ITN: spoken → written)
 let normalizedResult = normalizer.normalize(result: asrResult)
 print(normalizedResult.text)  // Written form
 ```
 
 ### Linking the Native Library
 
-To enable ITN support, link your app against `libnemo_text_processing`:
+To enable text processing support, link your app against `libnemo_text_processing`:
 
 1. Build text-processing-rs for your target platform
 2. Add the library to your Xcode project's linker settings

README.md

@@ -123,7 +123,7 @@ Enhance ASR output with post-processing:
 
 | Tool | Description | Language |
 |------|-------------|----------|
-| **[text-processing-rs](https://github.com/FluidInference/text-processing-rs)** | Inverse Text Normalization (ITN) - converts spoken-form ASR output to written form ("two hundred" → "200", "five dollars" → "$5"). Rust port of [NVIDIA NeMo Text Processing](https://github.com/NVIDIA/NeMo-text-processing) with Swift wrapper. | Rust, Swift |
+| **[text-processing-rs](https://github.com/FluidInference/text-processing-rs)** | Inverse Text Normalization (ITN) and Text Normalization (TN) across 7 languages (EN, DE, ES, FR, HI, JA, ZH). 100% NeMo test compatibility (3,011 tests). Converts spoken-form ASR output to written form ("two hundred" → "200", "five dollars" → "$5"). Rust port of [NVIDIA NeMo Text Processing](https://github.com/NVIDIA/NeMo-text-processing) with Swift wrapper. | Rust, Swift |
 
 ## Configuration