Sign in to access this content
Model
Spanish Conformer ASR model trained on ASR set 2.0.
Sign in to access this content
| Field | Response |
|---|---|
| Intended Application(s) & Domain(s): | Transcription of speech to text used in Contact Center Transcription, Video Conferencing Transcription, Virtual Assistants, etcetera |
| Model Type: | Speech Recognition |
| Intended Users: | Data scientists in contact center transcription, video conferencing transcription, and virtual assistants. |
| Output: | Transcribed text with timestamps and confidence scores |
| List the steps explaining how this model works: | Model takes Audio as input and provides text as output |
| Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Age, Gender, National Origin |
| Technical Limitations: | Transcripts are not 100% accurate. Accuracy varies based on the characteristics of input audio (Domain, Use Case, Accent, Noise, Speech Type, Context of speech, etc) |
| Verified to have met NVIDIA prescribed standards: | Yes |
| Performance Metrics: | Word Error Rate (WER), Silence Robustness (Characters/mins of silent audio), Latency (in milliseconds), Throughput (Total audio processed per unit of time) |
| Potential Known Risks: | Not recommended for word-for-word transcription as accuracy varies based on the characteristics of input audio (domain, use case, accent, noise, speech type, and context of speech) |
| Recommended Training: | https://www.nvidia.com/en-us/on-demand/session/gtcfall22-a41089/ |
| Licensing: | https://www.developer.nvidia.com/riva/ga/license |