lucataco/seamless_communication ❓📝🖼️🔢 → ❓

▶️ 914 runs 📅 Dec 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License

speech-to-text speech-translation text-to-speech

About

FacebookResearch/SeamlessM4T v2 - Massively Multilingual & Multimodal Machine Translation

Example Output

Output

{"text_output":"Mon animal préféré, c'est l'éléphant.","audio_output":"https://replicate.delivery/pbxt/6dPxbnvciRKmNBVlfHGnuelSwPA6dQSAKf05fjxB0696e5egE/out.wav"}

Performance Metrics

11.32s Prediction Time

136.59s Total Time

All Input Parameters

{
  "task_name": "S2ST (Speech to Speech translation)",
  "input_audio": "https://replicate.delivery/pbxt/K4oyjNRg7zgO3bfT9LKI9of4A6w9reAlXkyWzZeZONrz2mVY/demo-speech.mp3",
  "input_text_language": "English",
  "max_input_audio_length": 60,
  "target_language_text_only": "French",
  "target_language_with_speech": "French"
}

Input Parameters

task_name Default: S2ST (Speech to Speech translation): Choose a task
input_text Type: string: Provide input for tasks with text: T2ST and T2TT
input_audio Type: string: Provide input file for tasks with speech input: S2ST, S2TT and ASR
input_text_language Default: English: Specify language of the input_text for T2ST and T2TT
max_input_audio_length Type: numberDefault: 60: Set maximum input audio length.
target_language_text_only Default: French: Set target language for tasks with text output only: S2TT, T2TT and ASR.
target_language_with_speech Default: French: Set target language for tasks with speech output: S2ST or T2ST. Less languages are available for speech compared to text output.

Output Schema

text_output Type: string: Text Output
audio_output Type: stringFormat: uri: Audio Output

Version Details

Version ID: b61de43a89a30bb31baa14ba81647303accb8220975ea91268a447650f013298
Version Created: December 19, 2023

Run on Replicate →