From 997374b88fe6b2ae5cb4dcaf47d78cb3eff09fc2 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 11 六月 2024 19:56:52 +0800
Subject: [PATCH] add ctc inference code (#1806)
---
funasr/auto/auto_model.py | 9 +++++++--
1 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 9b4f6d9..047e652 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -233,6 +233,8 @@
# fp16
if kwargs.get("fp16", False):
model.to(torch.float16)
+ elif kwargs.get("bf16", False):
+ model.to(torch.bfloat16)
return model, kwargs
def __call__(self, *args, **cfg):
@@ -388,7 +390,6 @@
):
max_len_in_batch = max(max_len_in_batch, sample_length)
end_idx += 1
- results_sorted.append({'key': 'bad_data', 'text': '', 'timestamp': []})
continue
speech_j, speech_lengths_j = slice_padding_audio_samples(
@@ -418,7 +419,7 @@
end_idx += 1
max_len_in_batch = sample_length
if len(results) < 1:
- results.append({'key': 'bad_data', 'text': '', 'timestamp': []})
+ continue
results_sorted.extend(results)
# end_asr_total = time.time()
@@ -428,6 +429,10 @@
# f"time_speech_total_per_sample: {time_speech_total_per_sample: 0.3f}, "
# f"time_escape_total_per_sample: {time_escape_total_per_sample:0.3f}")
+ if len(results_sorted) != n:
+ results_ret_list.append({"key": key, "text": "", "timestamp": []})
+ logging.info("decoding, utt: {}, empty result".format(key))
+ continue
restored_data = [0] * n
for j in range(n):
index = sorted_data[j][1]
--
Gitblit v1.9.1