Translate Spanish video to English
Spanish is the language the model hears best, with 5.6% of words wrong, and it translates it into English at 18.2 BLEU with Accurate, in OpenAI’s figures.
Drop your video here
Choose your videoMP4, MOV, WebM or MKV. It opens right here, on your device.
- Nothing uploaded
- No sign-up
- No watermark
How well it translates Spanish into English
| Model in Shycut | BLEU into English | From the paper |
|---|---|---|
| Accurate (Whisper small) | 18.2 | Table 14, “Whisper small” row, Spanish column · OpenAI |
| Fast (Whisper base) | 12.4 | Table 14, “Whisper base” row, Spanish column · OpenAI |
BLEU compares a machine translation with human ones; higher is closer. These are OpenAI’s scores on the FLEURS set.
Accurate scores 1.5 times as high as Fast here, so a translate link opens Shycut with Accurate chosen.
How often it gets a Spanish word wrong
| Model in Shycut | Word error rate | Roughly | From the paper |
|---|---|---|---|
| Accurate (Whisper small) | 5.6% | 1 word in 18 | Table 13, “Whisper small” row, Spanish column · OpenAI |
| Fast (Whisper base) | 9.9% | 1 word in 10 | Table 13, “Whisper base” row, Spanish column · OpenAI |
Word error rate is the share of words a model gets wrong (swapped, missed or added) against a human transcript, in OpenAI’s own test on the FLEURS speech set; lower is better.
Shycut runs these two models converted to work in a browser (with 8-bit or 4-bit weights on some devices), so its results can differ a little from the paper’s.
How the translation is made
- While it listens
- The speech model writes English as it hears the Spanish: no separate translation step, and nothing is sent anywhere.
- Timed to the speech
- Each line follows the speech it translates; the timing of single words is approximate, since English word order differs.
- Kept apart from the script
- English words aren’t the ones said, so Shycut doesn’t use them to cut the video or find hesitations; the Text tab offers to write the speech as spoken.
Heard best, translated middling
Spanish is transcribed more accurately than any other language Shycut offers, yet it translates fifth of 9: hearing a language well and translating it well are measured separately.
If your viewers read Spanish, captions as spoken are the more faithful choice. For English viewers, translate with Accurate (18.2 BLEU against 12.4 for Fast) and read the lines through.
How to do it in Shycut
Open your video
The button opens Shycut set to translate Spanish speech into English, with the Accurate model chosen.
Write the English captions
The model listens to the speech and writes English lines, timed to it, on your device.
Check, then save
Read the lines through, correct what needs it, then save the video with them or download an SRT file.
Where these facts come from
Questions
How good is the Spanish to English translation?
18.2 BLEU for Accurate and 12.4 for Fast, in OpenAI’s test.
Should I translate or keep Spanish captions?
Spanish captions are the more accurate (5.6% of words wrong); translate when your audience needs English.
Do I need to install anything?
No. Shycut runs in your browser; the model downloads once.
Your video stays with you.
Open Shycut, drop the video in and export. Free, with no account, and your video never leaves your device.
Choose your video