> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/XDcobra/react-native-sherpa-onnx/llms.txt
> Use this file to discover all available pages before exploring further.
# STT Models Overview
> Overview of all speech-to-text model types supported by react-native-sherpa-onnx
# Speech-to-Text Models Overview
react-native-sherpa-onnx supports a wide range of speech-to-text (STT) model architectures, from fast streaming transducers to multilingual models like Whisper. This guide helps you choose the right model for your use case.
## Model Comparison
Fast streaming recognition with excellent accuracy. Best for real-time use cases.
Non-autoregressive ASR. Fast batch processing with high accuracy.
Multilingual, robust zero-shot recognition. Strong for diverse audio conditions.
Excellent for English and streaming. Good balance of speed and accuracy.
WeNet, SenseVoice, FunASR, Moonshine, and specialized models.
## Quick Comparison Table
| Model Type | Streaming | Multilingual | Speed | Use Case |
| ------------------------ | --------------- | ----------------- | --------- | ----------------------------------------- |
| **Zipformer/Transducer** | ✅ Yes | Depends | Fast | Real-time recognition, voice assistants |
| **LSTM Transducer** | ✅ Yes | Depends | Fast | Streaming ASR, mobile apps |
| **Paraformer** | ✅ Yes | Limited | Very Fast | Fast batch transcription |
| **Whisper** | ❌ No | ✅ Yes (90+ langs) | Medium | Multilingual transcription, diverse audio |
| **NeMo CTC** | ✅ Yes | Limited | Fast | English streaming, live captions |
| **WeNet CTC** | ❌ No | Limited | Fast | Compact deployment |
| **SenseVoice** | ❌ No | ✅ Yes | Medium | Emotion detection, punctuation |
| **FunASR Nano** | ❌ No | Limited | Medium | LLM-based ASR with prompts |
| **Moonshine** | ✅ Yes (v1 & v2) | Limited | Fast | Streaming-capable lightweight ASR |
| **Fire Red ASR** | ❌ No | Limited | Medium | Encoder-decoder ASR |
| **Dolphin** | ❌ No | Limited | Fast | Single-model CTC |
| **Canary** | ❌ No | ✅ Yes | Medium | Multilingual NeMo model |
| **Omnilingual** | ❌ No | ✅ Yes | Medium | Wide language coverage |
| **Tone CTC** | ✅ Yes | Limited | Very Fast | Lightweight streaming CTC |
## Choosing a Model
### For Real-Time Recognition (Streaming)
If you need **live recognition from a microphone**, choose one of these streaming-capable models:
* **Zipformer/Transducer** – Best overall for streaming, excellent accuracy
* **NeMo CTC** – Great for English streaming applications
* **Tone CTC** – Lightweight option for resource-constrained devices
* **LSTM Transducer** – LSTM-based streaming alternative
* **Paraformer** – Fast streaming with non-autoregressive approach
* **Moonshine** – Modern streaming-capable architecture
### For Batch/Offline Transcription
If you're transcribing **pre-recorded audio files**:
* **Whisper** – Best for multilingual content, robust to noise
* **Paraformer** – Fastest for single-language batch processing
* **SenseVoice** – When you need emotion labels and punctuation
* **Canary** – Multilingual with good accuracy
### By Language Support
**English Only:**
* NeMo CTC (streaming)
* Tone CTC (streaming)
* Many Zipformer variants
**Multilingual (90+ languages):**
* Whisper (offline)
* Canary (offline)
* Omnilingual (offline)
* SenseVoice (5 languages + emotion)
**Chinese:**
* Paraformer (excellent for Mandarin)
* FunASR Nano (LLM-based with prompts)
* SenseVoice (Chinese + emotion)
### By Device Constraints
**Low-end devices / limited RAM:**
* Tone CTC (lightweight streaming)
* Dolphin (compact single-model)
* WeNet CTC (compact deployment)
* Use `int8` quantized variants when available
**High-end devices:**
* Whisper (large models)
* Canary (multilingual)
* Full Zipformer models
## Model Detection
The SDK automatically detects model types based on folder name patterns and file layouts. You can also force a specific type:
```typescript theme={null}
import { createSTT, detectSttModel } from 'react-native-sherpa-onnx/stt';
// Auto-detect model type
const detectedInfo = await detectSttModel({
type: 'asset',
path: 'models/sherpa-onnx-whisper-tiny-en'
});
console.log(detectedInfo.modelType); // 'whisper'
// Create STT with auto-detection
const stt = await createSTT({
modelPath: { type: 'asset', path: 'models/sherpa-onnx-whisper-tiny-en' },
modelType: 'auto', // Auto-detect
preferInt8: true,
});
```
## Performance Tips
### Use Quantized Models
Set `preferInt8: true` to automatically use int8 quantized models when available:
```typescript theme={null}
const stt = await createSTT({
modelPath: { type: 'asset', path: 'models/whisper-tiny' },
preferInt8: true, // Faster inference, smaller memory footprint
});
```
### Adjust Thread Count
Increase threads on multi-core devices:
```typescript theme={null}
const stt = await createSTT({
modelPath: { type: 'asset', path: 'models/zipformer' },
numThreads: 4, // Use multiple cores
});
```
### Use Execution Providers
Leverage hardware acceleration:
```typescript theme={null}
const stt = await createSTT({
modelPath: { type: 'asset', path: 'models/paraformer' },
provider: 'nnapi', // Android NNAPI
// provider: 'xnnpack', // For XNNPACK
// provider: 'qnn', // Qualcomm QNN
});
```
See the [Execution Providers](/features/execution-providers) guide for more details.
## Download Links
All model downloads are available from the sherpa-onnx pretrained models repository:
* [Transducer Models](https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-transducer/index.html)
* [Paraformer Models](https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-paraformer/index.html)
* [Whisper Models](https://k2-fsa.github.io/sherpa/onnx/pretrained_models/whisper/index.html)
* [NeMo CTC Models](https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-ctc/nemo/index.html)
* [All STT Models](https://k2-fsa.github.io/sherpa/onnx/pretrained_models/index.html)
## Next Steps
Learn how to download and bundle models with your app
Detailed API documentation for speech recognition
Real-time recognition from microphone
Contextual biasing for improved accuracy