datong-new/tts-zh 📝❓ → ❓
Example Output
Output
Performance Metrics
14.93s
Prediction Time
14.95s
Total Time
All Input Parameters
{
"text": "散文是一种抒发作者真情实感、写作方式灵活的记叙类文学体裁。",
"voice_type": "Chinese_Cantonese_women"
}
Input Parameters
- text (required)
- input text
- voice_type (required)
Output Schema
- out
- Out
Example Execution Logs
2024-03-14 11:27:38,597 - modelscope - WARNING - Model revision not specified, use revision: v1.0.4
2024-03-14 11:27:39,230 - modelscope - INFO - initiate model from /src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k
2024-03-14 11:27:39,230 - modelscope - INFO - initiate model from location /src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k.
2024-03-14 11:27:39,232 - modelscope - INFO - initialize model from /src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k
2024-03-14 11:27:39,234 - modelscope - INFO - am_config=/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/am/config.yaml voc_config=/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/voc/config.yaml
2024-03-14 11:27:39,234 - modelscope - INFO - audio_config=/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/audio_config.yaml
2024-03-14 11:27:39,234 - modelscope - INFO - am_ckpts=OrderedDict([(980000, '/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/am/ckpt/checkpoint_980000.pth')])
2024-03-14 11:27:39,234 - modelscope - INFO - voc_ckpts=OrderedDict([(360000, '/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/voc/ckpt/checkpoint_360000.pth')])
2024-03-14 11:27:39,235 - modelscope - INFO - se_path=/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/am/se.npy se_model_path=/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/se/ckpt/se.onnx
2024-03-14 11:27:39,235 - modelscope - INFO - mvn_path=/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k/voices/F7/am/mvn.npy
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
Load pinyin_en_mix_dict failed
festival_initialize() called more than once
2024-03-14 11:27:44,300 - modelscope - WARNING - No preprocessor field found in cfg.
2024-03-14 11:27:44,300 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file.
2024-03-14 11:27:44,301 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/src/modelscope/speech_tts/speech_sambert-hifigan_tts_jiajia_Cantonese_16k'}. trying to build by task and model information.
2024-03-14 11:27:44,301 - modelscope - WARNING - No preprocessor key ('sambert-hifigan', 'text-to-speech') found in PREPROCESSOR_MAP, skip building preprocessor.
Removing weight norm...
Version Details
- Version ID
5f5a154a10d31a3fcce99c5a456ccb286c51172b335c7b833183f4f9f6f3624e- Version Created
- March 14, 2024