cjwbw/distil-whisper 🖼️❓🔢✓ → 📝

▶️ 277 runs 📅 Nov 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
speech-to-text

About

Distilled version of Whisper

Example Output

Output

others will be discontinued and need to be replaced by new benchmark rates.

Performance Metrics

2.35s Prediction Time
1343.03s Total Time
Input Parameters
audio (required) Type: string
Input audio file
model_name Default: distil-whisper/distil-large-v2
Choose a model.
max_new_tokens Type: integerDefault: 128
Maximum number of new tokens to output.
long_form_transcription Type: booleanDefault: false
Enable chunked algorithm to transcribe long-form audio files.
Output Schema

Output

Type: string

Version Details
Version ID
0a087deaca947454c2543451b52f74b9f05de21ff7848dc0e2b20d3e0ddfa100
Version Created
November 2, 2023
Run on Replicate →