Model reference · open weights
mms-all 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
Massively Multilingual Speech (MMS) - Finetuned ASR - ALL This checkpoint is a model fine-tuned for multi-lingual ASR and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and makes use of adapter models to transcribe 1000+ languages. The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 1162 languages. Table Of Content - Example - Supported Languages - Model details - Additional links Example This MMS checkpoint can be used with Transformers to transcribe audio of 1107 different languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to have at least transformers = 4.30 installed. If the 4.30 version is not yet available on PyPI make sure to install transformers from source: Next, we load a couple of audio samples via datasets. Make sure that the audio data is sampled to 16000 kHz. Next, we load the model and processor Now we process the audio data, pass the processed audio data to the model and transcribe the model output, just like we usually do for Wav2Vec2 models such as facebook/wav2vec2-base-960h We can now keep the same model in memory and simply switch out the language adapters by calling the convenient [loadadapter()]() function for the model and [settargetlang()]() for the tokenizer. We pass the target language as an input - "fra" for French. In the same way the language can be switched out for all other supported languages. Please have a look at: For more details, please have a look at the official docs. Supported Languages This model supports 1162 languages. Unclick the following to toogle all supported languages of this checkpoint in ISO 639-3 code. You can find more details about the languages and their ISO 649-3 codes in the MMS Language Coverage Overview. - abi - abk - abp - aca - acd - ace - acf - ach - acn - acr - acu - ade - adh - adj - adx - aeu - afr - agd - agg - agn - agr - agu - agx - aha - ahk - aia - aka - akb - ake - akp - alj - alp - alt - alz - ame - amf - amh - ami - amk - ann - any - aoz - apb - apr - ara - arl - asa - asg - asm - ast - ata - atb - atg -
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 965M |
| Variants | 1 |
| Runs with | transformers |
| Released | 2023-05-27 |
| Popularity | 255k downloads / month |
| Likes | 204 |
| 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 |
|---|---|---|---|---|---|
| mms-1b-all | 965M | BF16 | ~2.2 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys mms-all for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (mms-all 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="mms-all" -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 ↗