From c2f174cd7811a7a11e6227ecb371887f97fd66d3 Mon Sep 17 00:00:00 2001
From: 夜雨飘零 <yeyupiaoling@foxmail.com>
Date: 星期五, 02 二月 2024 23:06:13 +0800
Subject: [PATCH] Use ffmpeg read data (#1349)
---
funasr/models/whisper/model.py | 8 ++++++--
1 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/funasr/models/whisper/model.py b/funasr/models/whisper/model.py
index 6a6d47c..381a501 100644
--- a/funasr/models/whisper/model.py
+++ b/funasr/models/whisper/model.py
@@ -10,6 +10,8 @@
from funasr.models.whisper.utils.decoding import detect_language as detect_language_function, decode as decode_function
+from funasr.register import tables
+
@dataclass
class ModelDimensions:
@@ -128,6 +130,8 @@
return x
+
+@tables.register("encoder_classes", "WhisperEncoder")
class AudioEncoder(nn.Module):
def __init__(self, n_mels: int, n_ctx: int, n_state: int, n_head: int, n_layer: int):
super().__init__()
@@ -158,7 +162,7 @@
x = self.ln_post(x)
return x
-
+@tables.register("decoder_classes", "WhisperDecoder")
class TextDecoder(nn.Module):
def __init__(self, n_vocab: int, n_ctx: int, n_state: int, n_head: int, n_layer: int):
super().__init__()
@@ -193,7 +197,7 @@
return logits
-
+@tables.register("model_classes", "Whisper")
class Whisper(nn.Module):
def __init__(self, dims: dict):
super().__init__()
--
Gitblit v1.9.1