[Quantization] update README.md: pip install torch-quant

wanchen.swc

2023-03-17 fd0c0acd509204df760637e3886593c0413cb8a1

 funasr/models/e2e_uni_asr.py

@@ -206,7 +206,7 @@
            with torch.no_grad():
                speech_raw, encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
        else:
            speech_raw, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)
            speech_raw, encoder_out, encoder_out_lens = self.encode(speech, speech_lengths, ind=ind)

        intermediate_outs = None
        if isinstance(encoder_out, tuple):