From d72df6cd2f1914a749db0778233f3a66f447894a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 13 六月 2024 17:45:33 +0800
Subject: [PATCH] decoding
---
funasr/models/llm_asr/model.py | 19 ++++++++++++-------
1 files changed, 12 insertions(+), 7 deletions(-)
diff --git a/funasr/models/llm_asr/model.py b/funasr/models/llm_asr/model.py
index e1e331d..80c33fc 100644
--- a/funasr/models/llm_asr/model.py
+++ b/funasr/models/llm_asr/model.py
@@ -449,9 +449,9 @@
for name, param in model.named_parameters():
param.requires_grad = False
model.eval()
- self.llm = model
- llm_dim = model.get_input_embeddings().weight.shape[-1]
self.llm_dtype = llm_conf.get("llm_dtype", "fp32")
+ self.llm = model.to(dtype_map[self.llm_dtype])
+ llm_dim = model.get_input_embeddings().weight.shape[-1]
# adaptor
adaptor_class = tables.adaptor_classes.get(audio_adaptor)
@@ -496,11 +496,14 @@
batch_size, frames, _ = speech.shape
- # audio encoder
- encoder_out, encoder_out_lens = self.audio_encoder(speech.permute(0, 2, 1), speech_lengths)
+ with torch.cuda.amp.autocast(enabled=False):
+ # audio encoder
+ encoder_out, encoder_out_lens = self.audio_encoder(
+ speech.permute(0, 2, 1), speech_lengths
+ )
- # audio_adaptor
- encoder_out, encoder_out_lens = self.audio_adaptor(encoder_out, encoder_out_lens)
+ # audio_adaptor
+ encoder_out, encoder_out_lens = self.audio_adaptor(encoder_out, encoder_out_lens)
input_ids[input_ids < 0] = 0
inputs_embeds = self.llm.model.get_input_embeddings()(input_ids)
@@ -536,7 +539,9 @@
labels_ids[labels_ids == -1] = -100
attention_mask[attention_mask < 0] = 0
model_outputs = self.llm(
- inputs_embeds=inputs_embeds, attention_mask=attention_mask, labels=labels_ids
+ inputs_embeds=inputs_embeds.to(dtype_map[self.llm_dtype]),
+ attention_mask=attention_mask,
+ labels=labels_ids,
)
loss = model_outputs.loss
--
Gitblit v1.9.1