Jarbas commited on
Commit
6dae96d
·
verified ·
1 Parent(s): 9e10cf2

The model files at the repo root; the card lists the phoonnx voices

Browse files

Split by knowledge/wiki/audits/phoonnx-org-move/split_upload.py; every file is checked against the mirror by LFS sha256 or git blob id.

Files changed (1) hide show
  1. README.md +4 -6
README.md CHANGED
@@ -9,14 +9,15 @@ tags:
9
 
10
  # outetts-dac
11
 
12
- The `dac` model by OuteAI, from [Phoonnx/phoonnx-outetts](https://huggingface.co/Phoonnx/phoonnx-outetts), packaged for [phoonnx](https://github.com/TigreGotico/phoonnx), our ONNX text-to-speech library.
13
 
14
  ## Model details
15
 
16
  | | |
17
  |---|---|
18
  | Architecture | [OuteTTS](https://huggingface.co/collections/Phoonnx/outetts-6af8ecbd9994d1dfbb97f9fa) |
19
- | Source | [Phoonnx/phoonnx-outetts](https://huggingface.co/Phoonnx/phoonnx-outetts), folder `dac` |
 
20
  | Author | OuteAI |
21
 
22
  ## How to use
@@ -25,10 +26,7 @@ The phoonnx voice index does not list a voice for this model.
25
 
26
  ## Licence
27
 
28
- The source card records `license: other` for the whole repository, and says:
29
-
30
- > | Path | Source | License | |---|---|---| | `0.6B/model.onnx` (+ `model.onnx_data`), `0.6B/tokenizer.json` | [OuteAI/OuteTTS-1.0-0.6B-ONNX](https://huggingface.co/OuteAI/OuteTTS-1.0-0.6B-ONNX) | Apache-2.0 | | `1B/model.onnx` (+ `model.onnx_data`) | **re-exported by phoonnx** from [OuteAI/Llama-OuteTTS-1.0-1B](https://huggingface.co/OuteAI/Llama-OuteTTS-1.0-1B) - see below | **CC-BY-NC-SA-4.0 (non-commercial)** | | `1B/tokenizer.json` | [OuteAI/Llama-OuteTTS-1.0-1B-ONNX](https://huggingface.co/OuteAI/Llama-OuteTTS-1.0-1B-ONNX) | **CC-BY-NC-SA-4.0 (non-commercial)** | | `dac/decoder_model.onnx`, `dac/encoder_model.onnx`, `dac/config.json` | [OuteAI/DAC-speech-v1.0-ONNX](https://huggingface.co/OuteAI/DAC-speech-v1.0-ONNX) (weights: [ibm-research/DAC.speech.v1.0](https://huggingface.co/ibm-research/DAC.speech.v1.0)) | CDLA-Permissive-2.0 | | `speakers/en-female-1-neutral.json` | the `outetts` Python package (`version/v3/default_speakers`) | Apache-2.0 |
31
- > The two model sizes carry **different licenses**. The 0.6B is Apache-2.0 and covers 14 languages; phoonnx resolves those 14 to it. The 1B is CC-BY-NC-SA-4.0 - **not licensed for commercial use** - and is here because it is the only member of the family that covers Arabic, Belarusian, Bengali, Lithuanian, Persian, Portuguese, Swahili, Tamil and Ukrainian. Check the 1B license before you deploy it.
32
 
33
  ## Related projects
34
 
 
9
 
10
  # outetts-dac
11
 
12
+ A OuteTTS model by OuteAI, from [ibm-research/DAC.speech.v1.0](https://huggingface.co/ibm-research/DAC.speech.v1.0), packaged for [phoonnx](https://github.com/TigreGotico/phoonnx), our ONNX text-to-speech library.
13
 
14
  ## Model details
15
 
16
  | | |
17
  |---|---|
18
  | Architecture | [OuteTTS](https://huggingface.co/collections/Phoonnx/outetts-6af8ecbd9994d1dfbb97f9fa) |
19
+ | Upstream | [ibm-research/DAC.speech.v1.0](https://huggingface.co/ibm-research/DAC.speech.v1.0) |
20
+ | ONNX conversion | [OuteAI/DAC-speech-v1.0-ONNX](https://huggingface.co/OuteAI/DAC-speech-v1.0-ONNX) |
21
  | Author | OuteAI |
22
 
23
  ## How to use
 
26
 
27
  ## Licence
28
 
29
+ The upstream declares the licence `cdla-permissive-2.0` in the model card of ibm-research/DAC.speech.v1.0.
 
 
 
30
 
31
  ## Related projects
32