hf-seamless-m4t-large

• 📥 101 languages for speech input
• ⌨️ 96 Languages for text input/output
• 🗣️ 35 languages for speech output.

This is the "large" variant of the unified model, which enables multiple tasks without relying on multiple separate models:

• Speech-to-speech translation (S2ST)
• Speech-to-text translation (S2TT)
• Text-to-speech translation (T2ST)
• Text-to-text translation (T2TT)
• Automatic speech recognition (ASR)

You can perform all the above tasks from one single model, SeamlessM4TModel, but each task also has its own dedicated sub-model.

🤗 Usage

First, load the processor and a checkpoint of the model:

>>> from transformers import AutoProcessor, SeamlessM4TModel

>>> processor = AutoProcessor.from_pretrained("facebook/hf-seamless-m4t-large")
>>> model = SeamlessM4TModel.from_pretrained("facebook/hf-seamless-m4t-large")

You can seamlessly use this model on text or on audio, to generated either translated text or translated audio.

Here is how to use the processor to process text and audio:

>>> # let's load an audio sample from an Arabic speech corpus
>>> from datasets import load_dataset
>>> dataset = load_dataset("arabic_speech_corpus", split="test", streaming=True)
>>> audio_sample = next(iter(dataset))["audio"]

>>> # now, process it
>>> audio_inputs = processor(audios=audio_sample["array"], return_tensors="pt")

>>> # now, process some English test as well
>>> text_inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")

Speech

SeamlessM4TModel can seamlessly generate text or speech with few or no changes. Let's target Russian voice translation:

>>> audio_array_from_text = model.generate(**text_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()
>>> audio_array_from_audio = model.generate(**audio_inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()

With basically the same code, I've translated English text and Arabic speech to Russian speech samples.

Text

Similarly, you can generate translated text from audio files or from text with the same model. You only have to pass generate_speech=False to SeamlessM4TModel.generate. This time, let's translate to French.

>>> # from audio
>>> output_tokens = model.generate(**audio_inputs, tgt_lang="fra", generate_speech=False)
>>> translated_text_from_audio = processor.decode(output_tokens[0].tolist(), skip_special_tokens=True)

>>> # from text
>>> output_tokens = model.generate(**text_inputs, tgt_lang="fra", generate_speech=False)
>>> translated_text_from_text = processor.decode(output_tokens[0].tolist(), skip_special_tokens=True)

Tips

1. Use dedicated models

SeamlessM4TModel is transformers top level model to generate speech and text, but you can also use dedicated models that perform the task without additional components, thus reducing the memory footprint. For example, you can replace the audio-to-audio generation snippet with the model dedicated to the S2ST task, the rest is exactly the same code:

>>> from transformers import SeamlessM4TForSpeechToSpeech
>>> model = SeamlessM4TForSpeechToSpeech.from_pretrained("facebook/hf-seamless-m4t-large")

Or you can replace the text-to-text generation snippet with the model dedicated to the T2TT task, you only have to remove generate_speech=False.

>>> from transformers import SeamlessM4TForTextToText
>>> model = SeamlessM4TForTextToText.from_pretrained("facebook/hf-seamless-m4t-large")

Feel free to try out SeamlessM4TForSpeechToText and SeamlessM4TForTextToSpeech as well.

2. Change the speaker identity

You have the possibility to change the speaker used for speech synthesis with the spkr_id argument. Some spkr_id works better than other for some languages!

3. Change the generation strategy

You can use different generation strategies for speech and text generation, e.g .generate(input_ids=input_ids, text_num_beams=4, speech_do_sample=True) which will successively perform beam-search decoding on the text model, and