Model reference · open weights
seamless-m4t-large is an open-weight audio or speech model from facebook, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
SeamlessM4T v2 SeamlessM4T is our foundational all-in-one Massively Multilingual and Multimodal Machine Translation model delivering high-quality translation for speech and text in nearly 100 languages. SeamlessM4T models support the tasks of: - Speech-to-speech translation (S2ST) - Speech-to-text translation (S2TT) - Text-to-speech translation (T2ST) - Text-to-text translation (T2TT) - Automatic speech recognition (ASR). SeamlessM4T models support: - 🎤 101 languages for speech input. - 💬 96 Languages for text input/output. - 🔊 35 languages for speech output. 🌟 We are releasing SeamlessM4T v2, an updated version with our novel UnitY2 architecture. This new model improves over SeamlessM4T v1 in quality as well as inference speed in speech generation tasks. The v2 version of SeamlessM4T is a multitask adaptation of our novel UnitY2 architecture. Unity2 with its hierarchical character-to-unit upsampling and non-autoregressive text-to-unit decoding considerably improves over SeamlessM4T v1 in quality and inference speed. SeamlessM4T v2 is also supported by 🤗 Transformers, more on it in the dedicated section below. SeamlessM4T models We provide the extensive evaluation results of seamlessM4T-Large and SeamlessM4T-Medium reported in the paper (as averages) in the metrics files above. The evaluation data ids for FLEURS, CoVoST2 and CVSS-C can be found here Evaluating SeamlessM4T models To reproduce our results or to evaluate using the same metrics over your own test sets, please check out the Evaluation README here. Finetuning SeamlessM4T models Please check out the Finetuning README here. Transformers usage SeamlessM4T is available in the 🤗 Transformers library, requiring minimal dependencies. Steps to get started: 1. First install the 🤗 Transformers library from main and sentencepiece: 2. Run the following Python code to generate speech samples. Here the target language is Russian: 3. Listen to the audio samples either in an ipynb notebook: Or save them as a .wav file using a third-party library, e.g. scipy: For more details on using the SeamlessM4T model for inference using the 🤗 Transformers library, refer to the SeamlessM4T v2 docs or to this hands-on Google Colab
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 2.3B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2023-11-29 |
| Popularity | 332k downloads / month |
| Likes | 1,009 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| seamless-m4t-v2-large | 2.3B | BF16 | ~5.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys seamless-m4t-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (seamless-m4t-large below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="seamless-m4t-large" -F file=@audio.mp3
Licence
The weights are open but cc-by-nc-4.0 needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗