Saarika
Saarika is a high accuracy real-time speech recognition service optimized for a wide variety of audio inputs. It automatically detects the input language, transcribes the speech and outputs the transcript in the original language.
Saarika-v2.5 is our flagship speech recognition model, specifically designed for Indian languages and accents. It excels in handling complex multi-speaker conversations, telephony audio, and code-mixed speech with superior accuracy.
Key Features
Optimized for 8KHz telephony audio with enhanced noise handling and superior multi-speaker recognition capabilities.
Preserves proper nouns and entities accurately across languages, maintaining context and meaning in transcriptions.
Optional automatic language identification with LID output. Use “unknown” when language is not known for automatic detection.
Provides diarized outputs with precise timestamps for multi-speaker conversations through batch API processing.
Intelligently handles mid-sentence language switches in code-mixed speech, perfect for India’s multilingual conversations.
Comprehensive support for Indian languages with high accuracy in mixed-language environments.
Language Support
Saarika supports 11 languages: English, Hindi, Bengali, Tamil, Telugu, Kannada, Malayalam, Marathi, Gujarati, Punjabi, and Odia.
Languages (Code):
Hindi (hi-IN
), Bengali (bn-IN
), Tamil (ta-IN
), Telugu (te-IN
), Gujarati (gu-IN
), Kannada (kn-IN
), Malayalam (ml-IN
), Marathi (mr-IN
), Punjabi (pa-IN
), Odia (od-IN
), English (en-IN
)
Key Language Features
- English includes all dialects and accents
- Includes dialects and accents of the above languages
- Code-mixed audio support - Handles mixed-language content seamlessly
- Intelligent Proper Noun and Entity Preservation - Ensures proper nouns, regional names, and entities are recognized and retained accurately during transcription
Supports native script output in all of the above languages.
For automatic language detection, use language_code="unknown"
. The model will automatically identify the spoken language and return it in the response.
Performance Benchmarks
Saarika delivers exceptional accuracy across all supported languages, as measured on the VISTAAR Benchmark.
CER (Character Error Rate) Scores
Lower is better - Compared on VISTAAR Benchmark
- Across 11 Languages: 4.96%
- English: 4.45%
- Hindi: 4.42%
- 9 Other languages: 5.07%
WER (Word Error Rate) Scores
Lower is better - Compared on VISTAAR Benchmark
- Across 11 Languages: 18.32%
- English: 8.26%
- Hindi: 11.81%
- 9 Other languages: 20.15%
Detailed CER Performance by Language
CER (Character Error Rate) measures the percentage of characters that are wrong in a transcription. Lower scores are better, with 0% being perfect.
Key Capabilities
Basic Usage
Code-Mixed Speech
Automatic Language Detection
Basic transcription with specified language code. Perfect for single-language content with clear audio quality.