🚀 Initial push: Spark TTS fine-tuned on NonverbalTTS

.gitattributes

@@ -33,4 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-tokenizer.json filter=lfs diff=lfs merge=lfs -text
+LLM/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+wav2vec2-large-xlsr-53/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+LLM/model.safetensors filter=lfs diff=lfs merge=lfs -text
+BiCodec/model.safetensors filter=lfs diff=lfs merge=lfs -text
+src/figures/infer_control.png filter=lfs diff=lfs merge=lfs -text
+src/figures/infer_voice_cloning.png filter=lfs diff=lfs merge=lfs -text
+src/logo/HKUST.jpg filter=lfs diff=lfs merge=lfs -text
+src/logo/NPU.jpg filter=lfs diff=lfs merge=lfs -text
+src/logo/SJU.jpg filter=lfs diff=lfs merge=lfs -text
+src/logo/SparkTTS.png filter=lfs diff=lfs merge=lfs -text
+src/logo/mobvoi.jpg filter=lfs diff=lfs merge=lfs -text
+src/logo/mobvoi.png filter=lfs diff=lfs merge=lfs -text

BiCodec/config.yaml

@@ -0,0 +1,60 @@
+audio_tokenizer:
+  mel_params:
+    sample_rate: 16000
+    n_fft: 1024
+    win_length: 640
+    hop_length: 320
+    mel_fmin: 10 
+    mel_fmax: null
+    num_mels: 128
+
+  encoder:
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+    out_channels: 1024
+    sample_ratios: [1,1]
+
+  decoder:
+    input_channel: 1024
+    channels: 1536
+    rates: [8, 5, 4, 2]
+    kernel_sizes: [16,11,8,4]
+
+  quantizer:
+    input_dim: 1024
+    codebook_size: 8192
+    codebook_dim: 8
+    commitment: 0.25
+    codebook_loss_weight: 2.0
+    use_l2_normlize: True
+    threshold_ema_dead_code: 0.2
+  
+  speaker_encoder:
+    input_dim: 128
+    out_dim: 1024
+    latent_dim: 128
+    token_num: 32
+    fsq_levels: [4, 4, 4, 4, 4, 4]
+    fsq_num_quantizers: 1
+
+  prenet:
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+    out_channels: 1024
+    condition_dim: 1024
+    sample_ratios: [1,1]
+    use_tanh_at_final: False
+
+  postnet: 
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 6
+    out_channels: 1024
+    use_tanh_at_final: False
+
+

BiCodec/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9940cd48d4446e4340ced82d234bf5618350dd9f5db900ebe47a4fdb03867ec
+size 625518756

README.md

@@ -1,181 +1,208 @@
 ---
-license: apache-2.0
-tags:
-  - spark-tts
-  - text-to-speech
-  - nonverbal
-  - emotional
-  - audio
-  - speech-synthesis
-  - huggingface
+license: cc-by-nc-sa-4.0
 language:
-  - en
-model-index:
-  - name: SparkNV-Voice
-    results: []
+- en
+- zh
+tags:
+- text-to-speech
+library_tag: spark-tts
+base_model:
+- SparkAudio/Spark-TTS-0.5B
 ---
+<div>
+  <p style="margin-bottom: 0; margin-top: 0;">
+    <strong>See <a href="https://huggingface.co/collections/unsloth/text-to-speech-tts-models-68007ab12522e96be1e02155">our collection</a> for all our TTS model uploads.</strong>
+  </p>
+  <p style="margin-bottom: 0;">
+    <em>Learn to fine-tune TTS models - <a href="https://docs.unsloth.ai/basics/text-to-speech-tts-fine-tuning">Read our Guide</a>.</em>
+  </p>
+<p style="margin-top: 0;margin-bottom: 0;">
+    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; ">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://docs.unsloth.ai/basics/text-to-speech-tts-fine-tuning">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+<h1 style="margin-top: 0rem;">✨ Run & Fine-tune TTS models with Unsloth!</h1>
+</div>
+
+- Fine-tune TTS models for free using our Google [Colab notebooks here](https://docs.unsloth.ai/get-started/unsloth-notebooks#text-to-speech-tts-notebooks)!
+- Read our Blog about TTS support: [unsloth.ai/blog/tts](https://docs.unsloth.ai/basics/text-to-speech-tts-fine-tuning)
+
+| Unsloth supports          |    Free Notebooks                                                                                           | Performance | Memory use |
+|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
+| **Spark-TTS**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Spark_TTS_(0_5B).ipynb)               | 1.5x faster | 58% less |
+| **Whisper Large V3**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Whisper.ipynb)               | 1.5x faster | 50% less |
+| **Qwen3 (14B)**      | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks)               | 2x faster | 70% less |
+| **Llama 3.2 Vision (11B)**      | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb)               | 1.8x faster | 50% less |
+
+<div align="center">
+    <h1>
+    Spark-TTS
+    </h1>
+    <p>
+    Official model for <br>
+    <b><em>Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens</em></b>
+    </p>
+    <p>
+    <img src="src/logo/SparkTTS.jpg" alt="Spark-TTS Logo" style="width: 200px; height: 200px;">
+    </p>
+</div>
+
+
+## Spark-TTS 🔥
+
+### 👉🏻 [Spark-TTS Demos](https://sparkaudio.github.io/spark-tts/) 👈🏻
+
+### 👉🏻 [Github Repo](https://github.com/SparkAudio/Spark-TTS) 👈🏻
+
+### 👉🏻 [Paper](https://arxiv.org/pdf/2503.01710) 👈🏻
+
+### Overview
+
+Spark-TTS is an advanced text-to-speech system that uses the power of large language models (LLM) for highly accurate and natural-sounding voice synthesis. It is designed to be efficient, flexible, and powerful for both research and production use.
+
+### Key Features
+
+- **Simplicity and Efficiency**: Built entirely on Qwen2.5, Spark-TTS eliminates the need for additional generation models like flow matching. Instead of relying on separate models to generate acoustic features, it directly reconstructs audio from the code predicted by the LLM. This approach streamlines the process, improving efficiency and reducing complexity.
+- **High-Quality Voice Cloning**: Supports zero-shot voice cloning, which means it can replicate a speaker's voice even without specific training data for that voice. This is ideal for cross-lingual and code-switching scenarios, allowing for seamless transitions between languages and voices without requiring separate training for each one.
+- **Bilingual Support**: Supports both Chinese and English, and is capable of zero-shot voice cloning for cross-lingual and code-switching scenarios, enabling the model to synthesize speech in multiple languages with high naturalness and accuracy.
+- **Controllable Speech Generation**: Supports creating virtual speakers by adjusting parameters such as gender, pitch, and speaking rate.
 
-# 🔊 SparkNV-Voice
+---
 
-**SparkNV-Voice** is a fine-tuned version of the [Spark-TTS](https://huggingface.co/suno-ai/spark-tts) model trained on the [NonverbalTTS](https://huggingface.co/datasets/deepvk/NonverbalTTS) dataset. It enables expressive speech synthesis with **nonverbal cues** (like laughter, sighs, sneezing, etc.) and rich emotional tone.
+<table align="center">
+  <tr>
+    <td align="center"><b>Inference Overview of Voice Cloning</b><br><img src="src/figures/infer_voice_cloning.png" width="80%" /></td>
+  </tr>
+  <tr>
+    <td align="center"><b>Inference Overview of Controlled Generation</b><br><img src="src/figures/infer_control.png" width="80%" /></td>
+  </tr>
+</table>
 
-Built for applications that require **natural, human-like vocalization**, this model produces speech with **semantic tokens** and **global prosody control** using BiCodec detokenization.
 
----
+## Install
+**Clone and Install**
 
-## 🧾 Model Details
+- Clone the repo
+``` sh
+git clone https://github.com/SparkAudio/Spark-TTS.git
+cd Spark-TTS
+```
 
-- **Base**: `suno-ai/spark-tts`
-- **Dataset**: [`deepvk/NonverbalTTS`](https://huggingface.co/datasets/deepvk/NonverbalTTS)
-- **Architecture**: Causal Language Model + BiCodec for audio token generation
-- **Language**: English
-- **Voice**: Single-speaker (no multi-speaker conditioning)
+- Install Conda: please see https://docs.conda.io/en/latest/miniconda.html
+- Create Conda env:
 
----
+``` sh
+conda create -n sparktts -y python=3.12
+conda activate sparktts
+pip install -r requirements.txt
+# If you are in mainland China, you can set the mirror as follows:
+pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
+```
 
-## 🚀 Inference Code
+**Model Download**
 
+Download via python:
 ```python
-import torch
-import re
-import numpy as np
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import soundfile as sf
-from IPython.display import Audio, display
-
-# Load model and tokenizer
-model = AutoModelForCausalLM.from_pretrained("yasserrmd/SparkNV-Voice", torch_dtype=torch.float16).to("cuda")
-tokenizer = AutoTokenizer.from_pretrained("yasserrmd/SparkNV-Voice")
-
-# Optional: load BiCodec-based audio_tokenizer
-from models.audio_codec.bicodec_tokenizer import BiCodecTokenizer
-audio_tokenizer = BiCodecTokenizer.from_pretrained("suno-ai/spark-tts", device="cuda")
-
-# Enable fast inference
-from models.fastmodel_patch import FastModel
-FastModel.for_inference(model)
-
-@torch.inference_mode()
-def generate_speech_from_text(
-    text: str,
-    temperature: float = 0.8,
-    top_k: int = 50,
-    top_p: float = 1.0,
-    max_new_audio_tokens: int = 2048,
-    device: torch.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-) -> np.ndarray:
-
-    torch.compiler.reset()
-
-    prompt = "<|task_tts|><|start_content|>" + text + "<|end_content|><|start_global_token|>"
-    model_inputs = tokenizer([prompt], return_tensors="pt").to(device)
-
-    print("Generating token sequence...")
-    generated_ids = model.generate(
-        **model_inputs,
-        max_new_tokens=max_new_audio_tokens,
-        do_sample=True,
-        temperature=temperature,
-        top_k=top_k,
-        top_p=top_p,
-        eos_token_id=tokenizer.eos_token_id,
-        pad_token_id=tokenizer.pad_token_id
-    )
-    print("Token sequence generated.")
-
-    generated_ids_trimmed = generated_ids[:, model_inputs.input_ids.shape[1]:]
-    predicts_text = tokenizer.batch_decode(generated_ids_trimmed, skip_special_tokens=False)[0]
-
-    # Extract semantic tokens
-    semantic_matches = re.findall(r"<\|bicodec_semantic_(\d+)\|>", predicts_text)
-    if not semantic_matches:
-        print("⚠️ No semantic tokens found.")
-        return np.array([], dtype=np.float32)
-
-    pred_semantic_ids = torch.tensor([int(token) for token in semantic_matches]).long().unsqueeze(0)
-
-    # Extract global tokens
-    global_matches = re.findall(r"<\|bicodec_global_(\d+)\|>", predicts_text)
-    if not global_matches:
-        print("⚠️ No global tokens found. Using zeros.")
-        pred_global_ids = torch.zeros((1, 1), dtype=torch.long)
-    else:
-        pred_global_ids = torch.tensor([int(token) for token in global_matches]).long().unsqueeze(0)
-
-    pred_global_ids = pred_global_ids.unsqueeze(0)
-
-    print(f"🎯 Found {pred_semantic_ids.shape[1]} semantic tokens.")
-    print(f"🎯 Found {pred_global_ids.shape[2]} global tokens.")
-
-    # Detokenize audio
-    audio_tokenizer.device = device
-    audio_tokenizer.model.to(device)
-    wav_np = audio_tokenizer.detokenize(
-        pred_global_ids.to(device).squeeze(0),
-        pred_semantic_ids.to(device)
-    )
-    print("✅ Detokenization complete.")
-
-    return wav_np
-
-
-# === Usage ===
-input_text = "Hey there my name is Yasser, and I'm a 🌬️ speech generation model that can sound like a person."
-generated_waveform = generate_speech_from_text(input_text)
-
-if generated_waveform.size > 0:
-    sample_rate = audio_tokenizer.config.get("sample_rate", 16000)
-    sf.write("generated_speech.wav", generated_waveform, sample_rate)
-    print("💾 Saved: generated_speech.wav")
-    display(Audio(generated_waveform, rate=sample_rate))
-else:
-    print("⚠️ Audio generation failed.")
-````
+from huggingface_hub import snapshot_download
 
----
+snapshot_download("SparkAudio/Spark-TTS-0.5B", local_dir="pretrained_models/Spark-TTS-0.5B")
+```
 
-## 🎛️ Supported Nonverbal Cues
+Download via git clone:
+```sh
+mkdir -p pretrained_models
 
-The model is fine-tuned on sequences containing:
+# Make sure you have git-lfs installed (https://git-lfs.com)
+git lfs install
 
-* `<|laughing|>`
-* `<|sighing|>`
-* `<|groaning|>`
-* `<|grunting|>`
-* `<|sniffing|>`
-* `<|sneezing|>`
-* `<|breathing|>`
-* `<|coughing|>`
-* `<|snoring|>`
-* `<|throat_clearing|>`
+git clone https://huggingface.co/SparkAudio/Spark-TTS-0.5B pretrained_models/Spark-TTS-0.5B
+```
 
-You can combine these with your prompt to guide tone/emotion or rely on semantic token generation.
+**Basic Usage**
 
----
+You can simply run the demo with the following commands:
+``` sh
+cd example
+bash infer.sh
+```
 
-## 🧠 Dataset Highlights: `NonverbalTTS`
+Alternatively, you can directly execute the following command in the command line to perform inference：
 
-* 17+ hours of annotated emotional & nonverbal English speech
-* Automatic + human-validated labels
-* Sources: VoxCeleb, Expresso
-* Paper: [arXiv:2507.13155](https://arxiv.org/abs/2507.13155)
+``` sh
+python -m cli.inference \
+    --text "text to synthesis." \
+    --device 0 \
+    --save_dir "path/to/save/audio" \
+    --model_dir pretrained_models/Spark-TTS-0.5B \
+    --prompt_text "transcript of the prompt audio" \
+    --prompt_speech_path "path/to/prompt_audio"
+```
 
----
+**UI Usage**
 
-## 📜 License
+You can start the UI interface by running `python webui.py`, which allows you to perform Voice Cloning and Voice Creation. Voice Cloning supports uploading reference audio or directly recording the audio.
 
-Apache 2.0 — free for commercial and academic use.
 
----
+| **Voice Cloning** | **Voice Creation** |
+|:-------------------:|:-------------------:|
+| ![Image 1](src/figures/gradio_TTS.png) | ![Image 2](src/figures/gradio_control.png) |
 
-## 🤝 Credits
 
-* Base model: [`suno-ai/spark-tts`](https://huggingface.co/suno-ai/spark-tts)
-* Dataset: [`deepvk/NonverbalTTS`](https://huggingface.co/datasets/deepvk/NonverbalTTS)
-* Author: [`@yasserrmd`](https://huggingface.co/yasserrmd)
+## To-Do List
 
----
+- [x] Release the Spark-TTS paper.
+- [ ] Release the training code.
+- [ ] Release the training dataset, VoxBox.
+
+## Citation
+
+```
+@misc{wang2025sparktts,
+      title={Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens}, 
+      author={Xinsheng Wang and Mingqi Jiang and Ziyang Ma and Ziyu Zhang and Songxiang Liu and Linqin Li and Zheng Liang and Qixi Zheng and Rui Wang and Xiaoqin Feng and Weizhen Bian and Zhen Ye and Sitong Cheng and Ruibin Yuan and Zhixian Zhao and Xinfa Zhu and Jiahao Pan and Liumeng Xue and Pengcheng Zhu and Yunlin Chen and Zhifei Li and Xie Chen and Lei Xie and Yike Guo and Wei Xue},
+      year={2025},
+      eprint={2503.01710},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2503.01710}, 
+}
+```
+
+
+## ⚠ License Update
+
+The model's license has been updated from Apache 2.0 to CC BY-NC-SA due to the licensing terms of some training data.
+
+Key Changes:
+
+- The model can only be used for non-commercial purposes.
+
+- Any modifications or derivatives must also be released under CC BY-NC-SA 4.0.
+
+- Proper attribution is required when using or modifying the model.
+
+Please ensure compliance with the new license terms.
+
+
+## ⚠️ Usage Disclaimer
+
+This project provides a zero-shot voice cloning TTS model intended for academic research, educational purposes, and legitimate applications, such as personalized speech synthesis, assistive technologies, and linguistic research.
+
+Please note:
+
+- Do not use this model for unauthorized voice cloning, impersonation, fraud, scams, deepfakes, or any illegal activities.
+
+- Ensure compliance with local laws and regulations when using this model and uphold ethical standards.
 
-## 💬 Feedback & Contributions
+- The developers assume no liability for any misuse of this model.
 
-Open a discussion or issue on this repo. Contributions are welcome!
+We advocate for the responsible development and use of AI and encourage the community to uphold safety and ethical principles in AI research and applications. If you have any concerns regarding ethics or misuse, please contact us.

config.yaml

@@ -0,0 +1,7 @@
+highpass_cutoff_freq: 40
+sample_rate: 16000 
+segment_duration: 2.4 # (s)
+max_val_duration: 12 # (s)
+latent_hop_length: 320
+ref_segment_duration: 6
+volume_normalize: true

wav2vec2-large-xlsr-53/README.md

@@ -0,0 +1,29 @@
+---
+language: multilingual
+datasets:
+- common_voice
+tags:
+- speech
+license: apache-2.0
+---
+
+# Wav2Vec2-XLSR-53 
+
+[Facebook's XLSR-Wav2Vec2](https://ai.facebook.com/blog/wav2vec-20-learning-the-structure-of-speech-from-raw-audio/)
+
+The base model pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. Note that this model should be fine-tuned on a downstream task, like Automatic Speech Recognition. Check out [this blog](https://huggingface.co/blog/fine-tune-wav2vec2-english) for more information.
+
+[Paper](https://arxiv.org/abs/2006.13979)
+
+Authors: Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli
+
+**Abstract**
+This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72% compared to the best known results. On BABEL, our approach improves word error rate by 16% relative compared to a comparable system. Our approach enables a single multilingual speech recognition model which is competitive to strong individual models. Analysis shows that the latent discrete speech representations are shared across languages with increased sharing for related languages. We hope to catalyze research in low-resource speech understanding by releasing XLSR-53, a large model pretrained in 53 languages.
+
+The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.
+
+# Usage
+
+See [this notebook](https://colab.research.google.com/github/patrickvonplaten/notebooks/blob/master/Fine_Tune_XLSR_Wav2Vec2_on_Turkish_ASR_with_%F0%9F%A4%97_Transformers.ipynb) for more information on how to fine-tune the model.
+
+![model image](https://raw.githubusercontent.com/patrickvonplaten/scientific_images/master/xlsr_wav2vec2.png)

wav2vec2-large-xlsr-53/config.json

@@ -0,0 +1,83 @@
+{
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "transformers_version": "4.7.0.dev0",
+  "vocab_size": 32
+}

wav2vec2-large-xlsr-53/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

wav2vec2-large-xlsr-53/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314340227371a608f71adcd5f0de5933824fe77e55822aa4b24dba9c1c364dcb
+size 1269737156