Skip to content

How to adjust speech rate with ssml format #88

@hzl256

Description

@hzl256

from modelscope.outputs import OutputKeys
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

from modelscope.models.audio.tts import SambertHifigan
import os
import time

model_dir = "/home/gpu/KAN-TTS/pretrain_work_dir/" # the path of my trained speech model

custom_infer_abs = {
'voice_name':'F7',
'am_ckpt': os.path.join(model_dir, 'tmp_am', 'ckpt'),
'am_config': os.path.join(model_dir, 'tmp_am', 'config.yaml'),
'voc_ckpt':os.path.join(model_dir, 'orig_model', 'basemodel_16k', 'hifigan', 'ckpt'),
'voc_config':os.path.join(model_dir, 'orig_model', 'basemodel_16k', 'hifigan', 'config.yaml'),
'audio_config':os.path.join(model_dir, 'data', 'audio_config.yaml'),
'se_file':os.path.join(model_dir, 'data', 'se', 'se.npy')
}

kwargs = {'custom_ckpt': custom_infer_abs}

model_id = SambertHifigan(os.path.join(model_dir, "orig_model"), **kwargs)

sambert_hifigan_tts = pipeline(task=Tasks.text_to_speech, model=model_id)

txt = "<speak rate="1.5">我的语速比正常人慢。"

output = sambert_hifigan_tts(input=text)

wav = output[OutputKeys.OUTPUT_WAV]

with open('output.wav', 'wb') as f:
f.write(wav)

========================>
try diffrent text like next:
txt = "<speak rate="200">我的语速比正常人慢。"
txt = "<speak rate="-200">我的语速比正常人慢。"
txt = "<speak rate="0.5">我的语速比正常人慢。"
txt = "<speak rate="1.5">我的语速比正常人慢。"

get "output.wav" that have same speech rate.
the context is right. but the speech rate is same. why?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions