fix paramter 'quantize' unused issue (#1813)

Marlowe

2024-06-14 6fd83d23ee64280d30fd99f0fe2ca0f52903dca1

 funasr/datasets/openai_datasets/datasets.py

@@ -51,7 +51,7 @@
        self.batch_size = kwargs.get("batch_size")
        self.batch_type = kwargs.get("batch_type")
        self.prompt_ids_len = 0
        self.retry = kwargs.get("retry", 10)
        self.retry = kwargs.get("retry", 100)

        self.permute = False
        from funasr.frontends.whisper_frontend import WhisperFrontend
@@ -62,6 +62,8 @@
        self.pattern = re.compile(r"(<\|startofspeech\|>.*?<\|endofspeech\|>)")
        # self.kwargs = kwargs
        self.max_token_length = kwargs.get("max_token_length", 1024)
        self.batch_size_scale_ratio_max = kwargs.get("batch_size_scale_ratio_max", 1.5)
        self.batch_size_token_max = kwargs.get("batch_size_token_max", 2500)

    def get_source_len(self, index):
        item = self.index_ds[index]
@@ -154,12 +156,15 @@
                fbank_beg.append(fbank_beg_i)

            if len(input_ids) > self.max_token_length:
                logging.info(
                    f"input_ids > max_token_length: {len(input_ids)}>{self.max_token_length}, {item}"
                )
                badcase_flag = True
            if badcase_flag:
                continue
            input_ids = torch.tensor(input_ids, dtype=torch.int64)
            attention_mask = torch.tensor([len(input_ids)], dtype=torch.int32)
            labels = torch.tensor(labels, dtype=torch.int64)
            input_ids = torch.tensor(input_ids, dtype=torch.int64)  # [: self.max_token_length]
            attention_mask = torch.tensor([1] * len(input_ids), dtype=torch.int32)
            labels = torch.tensor(labels, dtype=torch.int64)  # [: self.max_token_length]

            fbank = speech[0, :, :]
            fbank_lens = speech_lengths
@@ -207,14 +212,11 @@

            if self.batch_type != "example":
                b, t = outputs["input_ids"].shape
                if b * t > self.batch_size * 2:
                    beg = torch.randint(0, 2, ()).item()
                    if b < 2:
                        beg = 0
                if b > 1 and b * t > self.batch_size_token_max:
                    logging.info(
                        f"Warning, b * t: {b * t} > {self.batch_size}, b: {b}, t: {t}, drop half data {idx}th, beg:{beg}"
                        f"Warning, {idx}th, b*t: {b}*{t}={b * t} > batch_size_sample_max: {self.batch_size_token_max}, drop last data"
                    )
                    samples = samples[beg : beg + b : 2]
                    samples = samples[:-1]
                    continue

            break