training/run_parler_tts_training.py [887:914]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if mixed_precision == "fp16":
            # fp16 doesn't work with T5-like models
            with accelerator.autocast(autocast_handler=autocast_kwargs):
                if training_args.parallel_mode.value != "distributed":
                    encoder_outputs = model.text_encoder(
                        input_ids=batch.get("input_ids"), attention_mask=batch.get("attention_mask", None)
                    )
                else:
                    encoder_outputs = model.module.text_encoder(
                        input_ids=batch.get("input_ids"), attention_mask=batch.get("attention_mask", None)
                    )
                # we optionnally project last_hidden_state to avoid recomputing every time
                encoder_hidden_states = encoder_outputs.last_hidden_state
                if (
                    config.text_encoder.hidden_size != config.decoder.hidden_size
                    and config.decoder.cross_attention_hidden_size is None
                ):
                    encoder_hidden_states = (
                        model.enc_to_dec_proj(encoder_hidden_states)
                        if training_args.parallel_mode.value != "distributed"
                        else model.module.enc_to_dec_proj(encoder_hidden_states)
                    )

                if batch.get("attention_mask", None) is not None:
                    encoder_hidden_states = encoder_hidden_states * batch.get("attention_mask", None)[..., None]

                encoder_outputs.last_hidden_state = encoder_hidden_states
                batch["encoder_outputs"] = encoder_outputs
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/run_parler_tts_training.py [935:962]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if mixed_precision == "fp16":
            # fp16 doesn't work with T5-like models
            with accelerator.autocast(autocast_handler=autocast_kwargs):
                if training_args.parallel_mode.value != "distributed":
                    encoder_outputs = model.text_encoder(
                        input_ids=batch.get("input_ids"), attention_mask=batch.get("attention_mask", None)
                    )
                else:
                    encoder_outputs = model.module.text_encoder(
                        input_ids=batch.get("input_ids"), attention_mask=batch.get("attention_mask", None)
                    )
                # we optionnally project last_hidden_state to avoid recomputing every time
                encoder_hidden_states = encoder_outputs.last_hidden_state
                if (
                    config.text_encoder.hidden_size != config.decoder.hidden_size
                    and config.decoder.cross_attention_hidden_size is None
                ):
                    encoder_hidden_states = (
                        model.enc_to_dec_proj(encoder_hidden_states)
                        if training_args.parallel_mode.value != "distributed"
                        else model.module.enc_to_dec_proj(encoder_hidden_states)
                    )

                if batch.get("attention_mask", None) is not None:
                    encoder_hidden_states = encoder_hidden_states * batch.get("attention_mask", None)[..., None]

                encoder_outputs.last_hidden_state = encoder_hidden_states
                batch["encoder_outputs"] = encoder_outputs
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -