Generate a singing voice prompt ALWAYS generates the same voice singing the same song about audiogpt HOT 1 OPEN

class T2S:
    def __init__(self, device= None):
        from inference.svs.ds_e2e import DiffSingerE2EInfer
        if device is None:
            device = 'cuda' if torch.cuda.is_available() else 'cpu'
        print("Initializing DiffSinger to %s" % device)
        self.device = device
        self.exp_name = 'checkpoints/0831_opencpop_ds1000'
        self.config= 'NeuralSeq/egs/egs_bases/svs/midi/e2e/opencpop/ds1000.yaml'
        self.set_model_hparams()
        self.pipe = DiffSingerE2EInfer(self.hp, device)
        self.default_inp = {
            'text': '你 说 你 不 SP 懂 为 何 在 这 时 牵 手 AP',
            'notes': 'D#4/Eb4 | D#4/Eb4 | D#4/Eb4 | D#4/Eb4 | rest | D#4/Eb4 | D4 | D4 | D4 | D#4/Eb4 | F4 | D#4/Eb4 | D4 | rest',
            'notes_duration': '0.113740 | 0.329060 | 0.287950 | 0.133480 | 0.150900 | 0.484730 | 0.242010 | 0.180820 | 0.343570 | 0.152050 | 0.266720 | 0.280310 | 0.633300 | 0.444590'
        }

    def set_model_hparams(self):
        set_hparams(config=self.config, exp_name=self.exp_name, print_hparams=False)
        self.hp = hp

    def inference(self, inputs):
        self.set_model_hparams()
        val = inputs.split(",")
        key = ['text', 'notes', 'notes_duration']
        try:
            inp = {k: v for k, v in zip(key, val)}
            wav = self.pipe.infer_once(inp)
        except:
            print('Error occurs. Generate default audio sample.\n')
            inp = self.default_inp
            wav = self.pipe.infer_once(inp)
        #if inputs == '' or len(val) < len(key):
        #    inp = self.default_inp
        #else:
        #    inp = {k:v for k,v in zip(key,val)}
        #wav = self.pipe.infer_once(inp)
        wav *= 32767
        audio_filename = os.path.join('audio', str(uuid.uuid4())[0:8] + ".wav")
        wavfile.write(audio_filename, self.hp['audio_sample_rate'], wav.astype(np.int16))
        print(f"Processed T2S.run, audio_filename: {audio_filename}")
        return audio_filename

class t2s_VISinger:
    def __init__(self, device=None):
        from espnet2.bin.svs_inference import SingingGenerate
        if device is None:
            device = 'cuda' if torch.cuda.is_available() else 'cpu'
        print("Initializing VISingere to %s" % device)
        tag = 'AQuarterMile/opencpop_visinger1'
        self.model = SingingGenerate.from_pretrained(
            model_tag=str_or_none(tag),
            device=device,
        )
        phn_dur = [[0.        , 0.219     ],
            [0.219     , 0.50599998],
            [0.50599998, 0.71399999],
            [0.71399999, 1.097     ],
            [1.097     , 1.28799999],
            [1.28799999, 1.98300004],
            [1.98300004, 7.10500002],
            [7.10500002, 7.60400009]]
        phn = ['sh', 'i', 'q', 'v', 'n', 'i', 'SP', 'AP']
        score = [[0, 0.50625, 'sh_i', 58, 'sh_i'], [0.50625, 1.09728, 'q_v', 56, 'q_v'], [1.09728, 1.9832100000000001, 'n_i', 53, 'n_i'], [1.9832100000000001, 7.105360000000001, 'SP', 0, 'SP'], [7.105360000000001, 7.604390000000001, 'AP', 0, 'AP']]
        tempo = 70
        tmp = {}
        tmp["label"] = phn_dur, phn
        tmp["score"] = tempo, score
        self.default_inp = tmp

    def inference(self, inputs):
        val = inputs.split(",")
        key = ['text', 'notes', 'notes_duration']
        try: # TODO: input will be update
            inp = {k: v for k, v in zip(key, val)}
            wav = self.model(text=inp)["wav"]
        except:
            print('Error occurs. Generate default audio sample.\n')
            inp = self.default_inp
            wav = self.model(text=inp)["wav"]

        audio_filename = os.path.join('audio', str(uuid.uuid4())[0:8] + ".wav")
        soundfile.write(audio_filename, wav, samplerate=self.model.fs)
        return audio_filename