isaacgv/vec2 🖼️❓🔢 → ❓

▶️ 106 runs 📅 Oct 2023 ⚙️ Cog 0.8.3

Example Output

Output

{"segments":[{"end":2.459,"text":" Vă face la fel și în acest caz.","start":0.34,"words":[{"end":0.804,"word":"Vă","score":0.166,"start":0.34},{"end":1.147,"word":"face","score":0.383,"start":0.865},{"end":1.309,"word":"la","score":0.5,"start":1.188},{"end":1.591,"word":"fel","score":0.361,"start":1.369},{"end":1.712,"word":"și","score":0.504,"start":1.632},{"end":1.834,"word":"în","score":0.506,"start":1.753},{"end":2.217,"word":"acest","score":0.365,"start":1.874},{"end":2.459,"word":"caz.","score":0.268,"start":2.278}]}],"detected_language":"ro"}

Performance Metrics

4.20s Prediction Time

4.05s Total Time

All Input Parameters

{
  "audio": "https://replicate.delivery/pbxt/JdiHR0a8YAD50La2BOcan3rBIuQsNfEREqwLYQo2U5s0t1hu/audio%20%283%29.mp3",
  "model": "large-v2",
  "temperature": 0
}

Input Parameters

audio (required) Type: string: Audio file
model Default: large-v2: Choose a Whisper model.
language: language spoken in the audio, specify None to perform language detection
temperature Type: numberDefault: 0: temperature to use for sampling

Output Schema

Output

Example Execution Logs

Transcribe with large-v2 model
Detected language: Romanian
  0%|          | 0/342 [00:00<?, ?frames/s]
100%|██████████| 342/342 [00:01<00:00, 323.52frames/s]
100%|██████████| 342/342 [00:01<00:00, 323.46frames/s]
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.

Version Details

Version ID: 2faa07c8f78bcb72c27bc4d6ee62bcc15fdda228e4a46c8434e6f3ccd2df34b7
Version Created: October 12, 2023

Run on Replicate →