Spaces:

nvidia
/

magpie_tts_multilingual_demo

Running on Zero

blisc commited on Jan 5

Commit

5ad8b18

1 Parent(s): f6e7eb3

update readme

Signed-off-by: Jason <jasoli@nvidia.com>

Files changed (1) hide show

app.py CHANGED Viewed

@@ -56,7 +56,7 @@ Note about the demo:
 - When the model runs on ZeroGPU Hardware, expect slower generation because the model checkpoint is loaded everytime.
 - As the model's speakers are all native English speakers, expect accented speech in the other languages.
 - The current model is limited to generations of up to 20 seconds. Generations past 20s will be truncated.
-- Loan words are not supported at this time: English characters in Mandarin will lead to unexpected results.
 - This current demo does not include MagpieTTS's robustness fix to avoid repeated words. Try the [MagpieTTS NIM](https://build.nvidia.com/nvidia/magpie-tts-multilingual) to test MagpieTTS robustness. Expect a fix for this demo soon.
 - For the enterprise offering, see the [MagpieTTS NIM](https://build.nvidia.com/nvidia/magpie-tts-multilingual) which includes additional native voices in the supported languages, emotional speech capabilities, and optimized batch and latency inference pipeline.
 """

 - When the model runs on ZeroGPU Hardware, expect slower generation because the model checkpoint is loaded everytime.
 - As the model's speakers are all native English speakers, expect accented speech in the other languages.
 - The current model is limited to generations of up to 20 seconds. Generations past 20s will be truncated.
+- Loan words are not supported at this time. For example, English characters in Mandarin will lead to unexpected results.
 - This current demo does not include MagpieTTS's robustness fix to avoid repeated words. Try the [MagpieTTS NIM](https://build.nvidia.com/nvidia/magpie-tts-multilingual) to test MagpieTTS robustness. Expect a fix for this demo soon.
 - For the enterprise offering, see the [MagpieTTS NIM](https://build.nvidia.com/nvidia/magpie-tts-multilingual) which includes additional native voices in the supported languages, emotional speech capabilities, and optimized batch and latency inference pipeline.
 """