From 4adb76a6edbca93aae7caa83382e764d7b058f07 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 08 五月 2024 19:21:58 +0800
Subject: [PATCH] Dev gzf exp (#1707)
---
funasr/models/sense_voice/model.py | 30 ++++++++++++++++++++++--------
1 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/funasr/models/sense_voice/model.py b/funasr/models/sense_voice/model.py
index 00bc85b..56e61e7 100644
--- a/funasr/models/sense_voice/model.py
+++ b/funasr/models/sense_voice/model.py
@@ -516,16 +516,23 @@
# Paramterts for rich decoding
self.beam_search.emo_unk = tokenizer.encode(
- DecodingOptions.get("emo_unk_token", "<|SPECIAL_TOKEN_1|>"), allowed_special="all")[0]
+ DecodingOptions.get("emo_unk_token", "<|SPECIAL_TOKEN_1|>"), allowed_special="all"
+ )[0]
self.beam_search.emo_unk_score = 1
self.beam_search.emo_tokens = tokenizer.encode(
- DecodingOptions.get("emo_target_tokens", "<|HAPPY|><|SAD|><|ANGRY|>"), allowed_special="all")
+ DecodingOptions.get("emo_target_tokens", "<|HAPPY|><|SAD|><|ANGRY|>"),
+ allowed_special="all",
+ )
self.beam_search.emo_scores = DecodingOptions.get("emo_target_threshold", [0.1, 0.1, 0.1])
self.beam_search.event_bg_token = tokenizer.encode(
- DecodingOptions.get("gain_tokens_bg", "<|Speech|><|BGM|><|Applause|><|Laughter|>"), allowed_special="all")
+ DecodingOptions.get("gain_tokens_bg", "<|Speech|><|BGM|><|Applause|><|Laughter|>"),
+ allowed_special="all",
+ )
self.beam_search.event_ed_token = tokenizer.encode(
- DecodingOptions.get("gain_tokens_ed", "<|/Speech|><|/BGM|><|/Applause|><|/Laughter|>"), allowed_special="all")
+ DecodingOptions.get("gain_tokens_ed", "<|/Speech|><|/BGM|><|/Applause|><|/Laughter|>"),
+ allowed_special="all",
+ )
self.beam_search.event_score_ga = DecodingOptions.get("gain_tokens_score", [1, 1, 1, 1])
encoder_out, encoder_out_lens = self.encode(
@@ -859,16 +866,23 @@
# Paramterts for rich decoding
self.beam_search.emo_unk = tokenizer.encode(
- DecodingOptions.get("emo_unk_token", "<|SPECIAL_TOKEN_1|>"), allowed_special="all")[0]
+ DecodingOptions.get("emo_unk_token", "<|SPECIAL_TOKEN_1|>"), allowed_special="all"
+ )[0]
self.beam_search.emo_unk_score = 1
self.beam_search.emo_tokens = tokenizer.encode(
- DecodingOptions.get("emo_target_tokens", "<|HAPPY|><|SAD|><|ANGRY|>"), allowed_special="all")
+ DecodingOptions.get("emo_target_tokens", "<|HAPPY|><|SAD|><|ANGRY|>"),
+ allowed_special="all",
+ )
self.beam_search.emo_scores = DecodingOptions.get("emo_target_threshold", [0.1, 0.1, 0.1])
self.beam_search.event_bg_token = tokenizer.encode(
- DecodingOptions.get("gain_tokens_bg", "<|Speech|><|BGM|><|Applause|><|Laughter|>"), allowed_special="all")
+ DecodingOptions.get("gain_tokens_bg", "<|Speech|><|BGM|><|Applause|><|Laughter|>"),
+ allowed_special="all",
+ )
self.beam_search.event_ed_token = tokenizer.encode(
- DecodingOptions.get("gain_tokens_ed", "<|/Speech|><|/BGM|><|/Applause|><|/Laughter|>"), allowed_special="all")
+ DecodingOptions.get("gain_tokens_ed", "<|/Speech|><|/BGM|><|/Applause|><|/Laughter|>"),
+ allowed_special="all",
+ )
self.beam_search.event_score_ga = DecodingOptions.get("gain_tokens_score", [1, 1, 1, 1])
encoder_out, encoder_out_lens = self.encode(
--
Gitblit v1.9.1