add loading torch models

雾聪

2024-03-13 2ea00f89b8e9c7f7635a141fa6328d8cf1ec3030

 funasr/models/qwen_audio/model.py

@@ -20,6 +20,11 @@
@tables.register("model_classes", "QwenAudio")
@tables.register("model_classes", "QwenAudioWarp")
class QwenAudioWarp(nn.Module):
    """
    Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
    https://arxiv.org/abs/2311.07919
    Modified from https://github.com/QwenLM/Qwen-Audio
    """
    def __init__(self, *args, **kwargs):
        super().__init__()

@@ -49,14 +54,13 @@

        meta_data = {}
        # meta_data["batch_data_time"] = -1

        sp_prompt = "<|startoftranscription|><|en|><|transcribe|><|en|><|notimestamps|><|wo_itn|>"
        query = f"<audio>{data_in[0]}</audio>{sp_prompt}"
        prompt = kwargs.get("prompt", "<|startoftranscription|><|en|><|transcribe|><|en|><|notimestamps|><|wo_itn|>")
        query = f"<audio>{data_in[0]}</audio>{prompt}"
        audio_info = self.tokenizer.process_audio(query)
        inputs = self.tokenizer(query, return_tensors='pt', audio_info=audio_info)
        inputs = inputs.to(self.model.device)
        pred = self.model.generate(**inputs, audio_info=audio_info)
        response = tokenizer.decode(pred.cpu()[0], skip_special_tokens=False, audio_info=audio_info)
        response = self.tokenizer.decode(pred.cpu()[0], skip_special_tokens=False, audio_info=audio_info)

        results = []
        result_i = {"key": key[0], "text": response}
@@ -72,6 +76,11 @@
@tables.register("model_classes", "QwenAudioChatWarp")
class QwenAudioChatWarp(nn.Module):
    def __init__(self, *args, **kwargs):
        """
        Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
        https://arxiv.org/abs/2311.07919
        Modified from https://github.com/QwenLM/Qwen-Audio
        """
        super().__init__()
        
        model_or_path = kwargs.get("model_path", "QwenAudio")