reach-vb HF staff commited on
Commit
ac892e6
1 Parent(s): 05da548

fairinternal -> facebookresearch

Browse files
Files changed (1) hide show
  1. README.md +7 -8
README.md CHANGED
@@ -3,6 +3,7 @@ inference: false
3
  tags:
4
  - SeamlessM4T
5
  license: cc-by-nc-4.0
 
6
  ---
7
 
8
  # SeamlessM4T Large
@@ -24,21 +25,19 @@ This is the "large" variant of the unified model, which enables multiple tasks w
24
 
25
  ## SeamlessM4T models
26
 
27
- The SeamlessM4T models come in two checkpoints of different size:
28
-
29
- | Model Name | #params | checkpoint | metrics |
30
- | - | - | - | - |
31
- | [SeamlessM4T-Medium]((https://huggingface.co/facebook/seamless-m4t-medium) | 1.2B | [checkpoint](https://huggingface.co/facebook/seamless-m4t-medium/resolve/main/multitask_unity_medium.pt) | [metrics]() |
32
- | [SeamlessM4T-Large](https://huggingface.co/facebook/seamless-m4t-large) | 2.3B | [checkpoint](https://huggingface.co/facebook/seamless-m4t-large/resolve/main/multitask_unity_large.pt) | [metrics]() |
33
 
34
  We provide extensive evaluation results of SeamlessM4T-Medium and SeamlessM4T-Large in the SeamlessM4T paper (as averages) in the `metrics` files above.
35
 
36
  ## Instructions to run inference with SeamlessM4T models
37
 
38
  The SeamlessM4T models are currently available through the `seamless_communication` package. The `seamless_communication`
39
- package can be installed by following the instructions outlined here: [Installation](https://github.com/fairinternal/seamless_communication/tree/main#installation).
40
 
41
- Once installed, a [`Translator`](https://github.com/fairinternal/seamless_communication/blob/590547965b343b590d15847a0aa25a6779fc3753/src/seamless_communication/models/inference/translator.py#L47)
42
  object can be instantiated to perform all five of the spoken langauge tasks. The `Translator` is instantiated with three arguments:
43
  1. **model_name_or_card**: SeamlessM4T checkpoint. Can be either `seamlessM4T_medium` for the medium model, or `seamlessM4T_large` for the large model
44
  2. **vocoder_name_or_card**: vocoder checkpoint (`vocoder_36langs`)
 
3
  tags:
4
  - SeamlessM4T
5
  license: cc-by-nc-4.0
6
+ library_name: fairseq2
7
  ---
8
 
9
  # SeamlessM4T Large
 
25
 
26
  ## SeamlessM4T models
27
 
28
+ | Model Name | #params | checkpoint | metrics |
29
+ | ------------------ | ------- | --------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------ |
30
+ | SeamlessM4T-Large | 2.3B | [🤗 Model card](https://huggingface.co/facebook/seamless-m4t-large) - [checkpoint](https://huggingface.co/facebook/seamless-m4t-large/resolve/main/multitask_unity_large.pt) | [metrics](https://dl.fbaipublicfiles.com/seamlessM4T/metrics/seamlessM4T_large.zip) |
31
+ | SeamlessM4T-Medium | 1.2B | [🤗 Model card](https://huggingface.co/facebook/seamless-m4t-medium) - [checkpoint](https://huggingface.co/facebook/seamless-m4t-medium/resolve/main/multitask_unity_medium.pt) | [metrics](https://dl.fbaipublicfiles.com/seamlessM4T/metrics/seamlessM4T_medium.zip) |
 
 
32
 
33
  We provide extensive evaluation results of SeamlessM4T-Medium and SeamlessM4T-Large in the SeamlessM4T paper (as averages) in the `metrics` files above.
34
 
35
  ## Instructions to run inference with SeamlessM4T models
36
 
37
  The SeamlessM4T models are currently available through the `seamless_communication` package. The `seamless_communication`
38
+ package can be installed by following the instructions outlined here: [Installation](https://github.com/facebookresearch/seamless_communication/tree/main#installation).
39
 
40
+ Once installed, a [`Translator`](https://github.com/facebookresearch/seamless_communication/blob/590547965b343b590d15847a0aa25a6779fc3753/src/seamless_communication/models/inference/translator.py#L47)
41
  object can be instantiated to perform all five of the spoken langauge tasks. The `Translator` is instantiated with three arguments:
42
  1. **model_name_or_card**: SeamlessM4T checkpoint. Can be either `seamlessM4T_medium` for the medium model, or `seamlessM4T_large` for the large model
43
  2. **vocoder_name_or_card**: vocoder checkpoint (`vocoder_36langs`)