bzikst/wav2vec2-large-xlsr-53-gender-recognition-librispeech 🖼️ → 📝

▶️ 5.6K runs 📅 Oct 2023 ⚙️ Cog 0.8.6 📄 Paper ⚖️ License
audio-classification speaker-gender-detection speaker-gender-recognition

About

Gender recognition for audio files

Example Output

Output

{'female': 0.001602, 'male': 0.998398}

Performance Metrics

2.33s Prediction Time
2.31s Total Time
Input Parameters
audio (required) Type: string
Audio file to identify gender, ffmepg will be used to cut first 30 secs and convert to 16kHz mono pcm_s16le
Output Schema

Output

Type: string

Version Details
Version ID
cae4655369236780e854a1e090c521186c01dab1f43945446092c3552623e26b
Version Created
October 16, 2023
Run on Replicate →