ai-models/speech_sambert-hifigan_tts_zh-cn_16k
2
0
Fork 0
mirror of https://www.modelscope.cn/iic/speech_sambert-hifigan_tts_zh-cn_16k.git synced 2026-04-02 18:32:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix sample code

Browse Source
This commit is contained in:
speech_tts
2022-10-17 04:15:56 +00:00
parent 1cff12db6b
commit 6aa160ec99
1 changed files with 6 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
README.md
View File

@ -92,19 +92,16 @@ widgets:
```Python ```Python
from scipy.io.wavfile import write from scipy.io.wavfile import write
from modelscope.metainfo import Pipelines from modelscope.outputs import OutputKeys
from modelscope.models import Model
from modelscope.pipelines import pipeline from modelscope.pipelines import pipeline
from modelscope.pipelines.outputs import OutputKeys from modelscope.utils.constant import Tasks
from modelscope.utils.constant import Tasks, Fields
text = '待合成文本' text = '待合成文本'
voice = 'zhitian_emo' model_id = 'damo/speech_sambert-hifigan_tts_zh-cn_16k'
model_id = 'damo\speech_sambert-hifigan_tts_zh-cn_16k'
sambert_hifigan_tts = pipeline(task=Tasks.text_to_speech, model=model_id) sambert_hifigan_tts = pipeline(task=Tasks.text_to_speech, model=model_id)
output = sambert_hifigan_tts(text, voice) output = sambert_hifigan_tts(input=text)
# save to file output.wav pcm = output[OutputKeys.OUTPUT_PCM]
write('output.wav', 16000, output[OutputKeys.OUTPUT_WAV]) write('output.wav', 16000, pcm)
``` ```
### 模型局限性以及可能的偏差 ### 模型局限性以及可能的偏差