From 5c28b4d6120d14351145b6edd6172f3eee132dd2 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 14 十月 2024 00:21:24 +0800
Subject: [PATCH] whisper-large-v3-turbo
---
examples/industrial_data_pretraining/paraformer-zh-spk/demo.py | 2 +-
funasr/frontends/default.py | 1 +
README.md | 14 +++++++-------
3 files changed, 9 insertions(+), 8 deletions(-)
diff --git a/README.md b/README.md
index 225dd13..a18ea9e 100644
--- a/README.md
+++ b/README.md
@@ -29,7 +29,7 @@
<a name="whats-new"></a>
## What's new:
-- 2024/10/10锛欰dded support for the Whisper-large-v3-turbo model, a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. It can be downloaded from the[modelscope](examples/industrial_data_pretraining/whisper/demo.py), and [openai](examples/industrial_data_pretraining/whisper/demo_from_openai.py).
+- 2024/10/10锛欰dded support for the Whisper-large-v3-turbo model, a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. It can be downloaded from the [modelscope](examples/industrial_data_pretraining/whisper/demo.py), and [openai](examples/industrial_data_pretraining/whisper/demo_from_openai.py).
- 2024/09/26: Offline File Transcription Service 4.6, Offline File Transcription Service of English 1.7锛孯eal-time Transcription Service 1.11 released锛宖ix memory leak & Support the SensevoiceSmall onnx model锛汧ile Transcription Service 2.0 GPU released, Fix GPU memory leak; ([docs](runtime/readme.md));
- 2024/09/25锛歬eyword spotting models are new supported. Supports fine-tuning and inference for four models: [fsmn_kws](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online), [fsmn_kws_mt](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online), [sanm_kws](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-offline), [sanm_kws_streaming](https://modelscope.cn/models/iic/speech_sanm_kws_phone-xiaoyun-commands-online).
- 2024/07/04锛歔SenseVoice](https://github.com/FunAudioLLM/SenseVoice) is a speech foundation model with multiple speech understanding capabilities, including ASR, LID, SER, and AED.
@@ -37,13 +37,13 @@
- 2024/06/27: Offline File Transcription Service GPU 1.0 released, supporting dynamic batch processing and multi-threading concurrency. In the long audio test set, the single-thread RTF is 0.0076, and multi-threads' speedup is 1200+ (compared to 330+ on CPU); ref to ([docs](runtime/readme.md))
- 2024/05/15锛歟motion recognition models are new supported. [emotion2vec+large](https://modelscope.cn/models/iic/emotion2vec_plus_large/summary)锛孾emotion2vec+base](https://modelscope.cn/models/iic/emotion2vec_plus_base/summary)锛孾emotion2vec+seed](https://modelscope.cn/models/iic/emotion2vec_plus_seed/summary). currently supports the following categories: 0: angry 1: happy 2: neutral 3: sad 4: unknown.
- 2024/05/15: Offline File Transcription Service 4.5, Offline File Transcription Service of English 1.6锛孯eal-time Transcription Service 1.10 released锛宎dapting to FunASR 1.0 model structure锛�([docs](runtime/readme.md))
+
+<details><summary>Full Changelog</summary>
+
- 2024/03/05锛欰dded the Qwen-Audio and Qwen-Audio-Chat large-scale audio-text multimodal models, which have topped multiple audio domain leaderboards. These models support speech dialogue, [usage](examples/industrial_data_pretraining/qwen_audio).
- 2024/03/05锛欰dded support for the Whisper-large-v3 model, a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. It can be downloaded from the[modelscope](examples/industrial_data_pretraining/whisper/demo.py), and [openai](examples/industrial_data_pretraining/whisper/demo_from_openai.py).
- 2024/03/05: Offline File Transcription Service 4.4, Offline File Transcription Service of English 1.5锛孯eal-time Transcription Service 1.9 released锛宒ocker image supports ARM64 platform, update modelscope锛�([docs](runtime/readme.md))
- 2024/01/30锛歠unasr-1.0 has been released ([docs](https://github.com/alibaba-damo-academy/FunASR/discussions/1319))
-
-<details><summary>Full Changelog</summary>
-
- 2024/01/30锛歟motion recognition models are new supported. [model link](https://www.modelscope.cn/models/iic/emotion2vec_base_finetuned/summary), modified from [repo](https://github.com/ddlBoJack/emotion2vec).
- 2024/01/25: Offline File Transcription Service 4.2, Offline File Transcription Service of English 1.3 released锛宱ptimized the VAD (Voice Activity Detection) data processing method, significantly reducing peak memory usage, memory leak optimization; Real-time Transcription Service 1.7 released锛宱ptimizatized the client-side锛�([docs](runtime/readme.md))
- 2024/01/09: The Funasr SDK for Windows version 2.0 has been released, featuring support for The offline file transcription service (CPU) of Mandarin 4.1, The offline file transcription service (CPU) of English 1.2, The real-time transcription service (CPU) of Mandarin 1.6. For more details, please refer to the official documentation or release notes([FunASR-Runtime-Windows](https://www.modelscope.cn/models/damo/funasr-runtime-win-cpu-x64/summary))
@@ -96,18 +96,18 @@
| Model Name | Task Details | Training Data | Parameters |
|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------:|:--------------------------------:|:----------:|
-| SenseVoiceSmall <br> ([猸怾(https://www.modelscope.cn/models/iic/SenseVoiceSmall) [馃](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) ) | multiple speech understanding capabilities, including ASR, ITN, LID, SER, and AED, support languages such as zh, yue, en, ja, ko | 300000 hours | 234M |
+| SenseVoiceSmall <br> ([猸怾(https://www.modelscope.cn/models/iic/SenseVoiceSmall) [馃](https://huggingface.co/FunAudioLLM/SenseVoiceSmall) ) | multiple speech understanding capabilities, including ASR, ITN, LID, SER, and AED, support languages such as zh, yue, en, ja, ko | 300000 hours | 234M |
| paraformer-zh <br> ([猸怾(https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) [馃](https://huggingface.co/funasr/paraformer-zh) ) | speech recognition, with timestamps, non-streaming | 60000 hours, Mandarin | 220M |
| <nobr>paraformer-zh-streaming <br> ( [猸怾(https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [馃](https://huggingface.co/funasr/paraformer-zh-streaming) )</nobr> | speech recognition, streaming | 60000 hours, Mandarin | 220M |
| paraformer-en <br> ( [猸怾(https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [馃](https://huggingface.co/funasr/paraformer-en) ) | speech recognition, without timestamps, non-streaming | 50000 hours, English | 220M |
| conformer-en <br> ( [猸怾(https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [馃](https://huggingface.co/funasr/conformer-en) ) | speech recognition, non-streaming | 50000 hours, English | 220M |
| ct-punc <br> ( [猸怾(https://modelscope.cn/models/damo/punc_ct-transformer_cn-en-common-vocab471067-large/summary) [馃](https://huggingface.co/funasr/ct-punc) ) | punctuation restoration | 100M, Mandarin and English | 290M |
| fsmn-vad <br> ( [猸怾(https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary) [馃](https://huggingface.co/funasr/fsmn-vad) ) | voice activity detection | 5000 hours, Mandarin and English | 0.4M |
-| fsmn-kws <br> ( [猸怾(https://modelscope.cn/models/iic/speech_charctc_kws_phone-xiaoyun/summary) ) | keyword spotting锛宻treaming | 5000 hours, Mandarin | 0.7M |
+| fsmn-kws <br> ( [猸怾(https://modelscope.cn/models/iic/speech_charctc_kws_phone-xiaoyun/summary) ) | keyword spotting锛宻treaming | 5000 hours, Mandarin | 0.7M |
| fa-zh <br> ( [猸怾(https://modelscope.cn/models/damo/speech_timestamp_prediction-v1-16k-offline/summary) [馃](https://huggingface.co/funasr/fa-zh) ) | timestamp prediction | 5000 hours, Mandarin | 38M |
| cam++ <br> ( [猸怾(https://modelscope.cn/models/iic/speech_campplus_sv_zh-cn_16k-common/summary) [馃](https://huggingface.co/funasr/campplus) ) | speaker verification/diarization | 5000 hours | 7.2M |
| Whisper-large-v3 <br> ([猸怾(https://www.modelscope.cn/models/iic/Whisper-large-v3/summary) [馃崁](https://github.com/openai/whisper) ) | speech recognition, with timestamps, non-streaming | multilingual | 1550 M |
-| Whisper-large-v3-turbo <br> ([猸怾(https://www.modelscope.cn/models/iic/Whisper-large-v3-turbo/summary) [馃崁](https://github.com/openai/whisper) ) | speech recognition, with timestamps, non-streaming | multilingual | 1550 M |
+| Whisper-large-v3-turbo <br> ([猸怾(https://www.modelscope.cn/models/iic/Whisper-large-v3-turbo/summary) [馃崁](https://github.com/openai/whisper) ) | speech recognition, with timestamps, non-streaming | multilingual | 809 M |
| Qwen-Audio <br> ([猸怾(examples/industrial_data_pretraining/qwen_audio/demo.py) [馃](https://huggingface.co/Qwen/Qwen-Audio) ) | audio-text multimodal models (pretraining) | multilingual | 8B |
| Qwen-Audio-Chat <br> ([猸怾(examples/industrial_data_pretraining/qwen_audio/demo_chat.py) [馃](https://huggingface.co/Qwen/Qwen-Audio-Chat) ) | audio-text multimodal models (chat) | multilingual | 8B |
| emotion2vec+large <br> ([猸怾(https://modelscope.cn/models/iic/emotion2vec_plus_large/summary) [馃](https://huggingface.co/emotion2vec/emotion2vec_plus_large) ) | speech emotion recongintion | 40000 hours | 300M |
diff --git a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
index 9afd801..d925a6e 100644
--- a/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
+++ b/examples/industrial_data_pretraining/paraformer-zh-spk/demo.py
@@ -9,7 +9,7 @@
model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch",
punc_model="iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch",
- spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
+ # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
)
res = model.generate(
diff --git a/funasr/frontends/default.py b/funasr/frontends/default.py
index 68bd6fb..6ea88d6 100644
--- a/funasr/frontends/default.py
+++ b/funasr/frontends/default.py
@@ -20,6 +20,7 @@
@tables.register("frontend_classes", "DefaultFrontend")
+@tables.register("frontend_classes", "EspnetFrontend")
class DefaultFrontend(nn.Module):
"""Conventional frontend structure for ASR.
Stft -> WPE -> MVDR-Beamformer -> Power-spec -> Mel-Fbank -> CMVN
--
Gitblit v1.9.1