Hugging Face's logo

hf-audio
/
xcodec-hubert-librispeech

Feature Extraction
Transformers
Safetensors
xcodec
Model card Files
xet
 Community
bezzam HF Staff commited on
Commit
bdc0d0b
·
verified ·
1 Parent(s): e17193c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -7,7 +7,15 @@ datasets:
7
 
8
  # X-Codec (speech, HuBERT)
9
 
10
- This codec is intended for speech data.
 
 
 
 
 
 
 
 
11
 
12
  Original model is `xcodec_hubert_librispeech` from [this table](https://github.com/zhenye234/xcodec?tab=readme-ov-file#available-models).
13
 
 
7
 
8
  # X-Codec (speech, HuBERT)
9
 
10
+ This codec is part of the X-Codec family of codecs as shown below:
11
+
12
+ | Model checkpoint | Semantic Model | Domain | Training Data |
13
+ |--------------------------------------------|-----------------------------------------------------------------------|---------------|-------------------------------|
14
+ | [xcodec-hubert-librispeech](https://huggingface.co/hf-audio/xcodec-hubert-librispeech) (this model) | [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) | Speech | Librispeech |
15
+ | [xcodec-wavlm-mls](https://huggingface.co/hf-audio/xcodec-wavlm-mls) | [microsoft/wavlm-base-plus](https://huggingface.co/microsoft/wavlm-base-plus)| Speech | MLS English |
16
+ | [xcodec-wavlm-more-data](https://huggingface.co/hf-audio/xcodec-wavlm-more-data) | [microsoft/wavlm-base-plus](https://huggingface.co/microsoft/wavlm-base-plus)| Speech | MLS English + Internal data |
17
+ | [xcodec-hubert-general](https://huggingface.co/hf-audio/xcodec-hubert-general) | [ZhenYe234/hubert_base_general_audio](https://huggingface.co/ZhenYe234/hubert_base_general_audio) | General audio | 200k hours internal data |
18
+ | [xcodec-hubert-general-balanced](https://huggingface.co/hf-audio/xcodec-hubert-general-balanced) | [ZhenYe234/hubert_base_general_audio](https://huggingface.co/ZhenYe234/hubert_base_general_audio) | General audio | More balanced data |
19
 
20
  Original model is `xcodec_hubert_librispeech` from [this table](https://github.com/zhenye234/xcodec?tab=readme-ov-file#available-models).
21