Name: Speech to text (STT) model
+ +Description :
+
+ The Kinyarwanda Speech-to-Text (STT) Model project is focused on creating an accurate machine learning model for transcribing spoken
+ Kinyarwanda into written text. With over 12 million speakers worldwide, Kinyarwanda is an important language to develop speech
+ recognition technology for.
+
+ The project will involve collecting a large dataset of spoken Kinyarwanda and using it to train a deep learning model. The model will be
+ evaluated using metrics such as accuracy and word error rate, and its performance will be compared to other existing STT models for
+ African languages.,
+ The ultimate goal of the project is to improve access to information and communication for Kinyarwanda speakers by enabling them to use
+ voice-enabled technology to interact with digital devices and services. Overall, the Kinyarwanda STT Model project has the potential to
+ make a significant impact in improving accessibility and inclusivity for Kinyarwanda speakers.
+
+
License : Speech to text (STT) model
+Scope :
+
+ The ultimate goal of the project is to improve access to information and communication for Kinyarwanda speakers by enabling them to use
+ voice-enabled technology to interact with digital devices and services. The project's scope appears to be focused on developing a
+ language model for Kinyarwanda specifically, with potential for future applications in speech recognition and natural language processing.
+
Timeline : Feb 2023 - March 2023
+Price : Free
+Contributors : Rene Promesse, Arnaud, Floris, Samuel
+Partners/Sponsors : MiniICT
+Metrics
+ +| Transcription accuracy: | +4.5 | + |
+
| Word Error Rate (WER): | +4.5 | + |
+
| Character Error Rate (CER): | +4.5 | + |
+
| Sentence Error Rate (SER): | +4.5 | + |
+
| Recognition Accuracy: | +4.5 | + |
+
| Latency: | +5s | + |
+
+ 
+ 
+ 
+ 
+ 